© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13353
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and political activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    377
    +0.18
    0.7%
    187
    +0.17
    0.6%
    421
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.09
    659
    +0.17
    0.06
    343
    +0.16
    0.06
    Negative Logits
    ensions
    -0.85
    ension
    -0.84
     Adin
    -0.83
    İĭ
    -0.82
     differential
    -0.82
    acter
    -0.80
    ention
    -0.80
     recourse
    -0.79
    Reference
    -0.79
    ractive
    -0.76
    POSITIVE LOGITS
    igans
    1.77
    igan
    1.41
    cia
    1.19
    agher
    1.15
    za
    1.12
    ja
    1.11
    ciating
    1.10
    cest
    1.10
    forth
    1.09
    ese
    1.08
    Activations Density 1.064%

    No Known Activations