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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 32672
    Prev
    Next
    INDEX
    Explanations

    religious or philosophical texts and historical or biographical information

    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
    735
    +0.04
    0.7%
    640
    +0.04
    0.6%
    6
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.04
    0.40
    640
    +0.04
    0.38
    6
    +0.03
    0.20
    Negative Logits
    imeter
    -0.22
    udget
    -0.21
    umers
    -0.21
    uron
    -0.21
    responsive
    -0.20
    usional
    -0.20
    ocused
    -0.20
    reatment
    -0.20
    quartered
    -0.20
    othal
    -0.19
    POSITIVE LOGITS
     Herod
    0.25
     CHRIST
    0.22
     Pratt
    0.21
     1908
    0.21
     Ibid
    0.21
     Agric
    0.21
     1888
    0.20
     Camb
    0.20
     Cf
    0.20
     Barn
    0.20
    Activations Density 21.841%

    No Known Activations