© 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. 35457
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusivity and community activism

    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
    +0.28
    1.1%
    497
    +0.13
    0.5%
    157
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.28
    0.10
    477
    +0.13
    0.07
    54
    +0.12
    0.09
    Negative Logits
    pose
    -0.69
    anga
    -0.67
    eln
    -0.67
    QL
    -0.66
    Son
    -0.65
    duc
    -0.64
    vern
    -0.63
    iger
    -0.63
     Kamp
    -0.62
     Horses
    -0.61
    POSITIVE LOGITS
     else
    1.75
     Else
    1.17
    THING
    1.16
     imaginable
    1.14
    else
    1.06
     conceivable
    0.96
    Else
    0.96
    body
    0.86
     except
    0.84
     who
    0.83
    Activations Density 6.394%

    No Known Activations