© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35635
    Prev
    Next
    INDEX
    Explanations

    an evaluative sentiment with a positive or negative connotation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.13
    0.6%
    208
    +0.10
    0.5%
    7
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.13
    0.24
    55
    +0.10
    0.27
    7
    +0.09
    0.21
    Negative Logits
     malls
    -0.60
    ĻĤ
    -0.59
     Turns
    -0.59
     Brief
    -0.58
     dunno
    -0.58
    anwhile
    -0.57
    often
    -0.56
     Advertisement
    -0.56
     Picture
    -0.56
     cue
    -0.55
    POSITIVE LOGITS
     è£ıç
    0.73
    omorphic
    0.72
    å¤
    0.70
    èª
    0.69
    ifiable
    0.69
    ãĤ¹ãĥĪ
    0.67
    ãĤª
    0.66
    ounters
    0.66
    osta
    0.66
    osher
    0.65
    Activations Density 16.407%

    No Known Activations