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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13701
    Prev
    Next
    INDEX
    Explanations

    phrases related to magnification or emphasis

    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
    62
    +0.10
    0.5%
    259
    +0.10
    0.5%
    383
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.19
    623
    +0.10
    0.04
    699
    +0.09
    0.01
    Negative Logits
    OPLE
    -0.80
    thia
    -0.74
    pta
    -0.74
     Alive
    -0.71
    hov
    -0.68
    TAG
    -0.66
    BOOK
    -0.66
    lde
    -0.65
    VEL
    -0.64
    AIN
    -0.63
    POSITIVE LOGITS
    olia
    1.11
    ificent
    1.06
    itudes
    0.96
    animous
    0.93
    ific
    0.90
     tremend
    0.83
     magn
    0.81
    itude
    0.78
     suspic
    0.76
    amic
    0.76
    Activations Density 7.932%

    No Known Activations