© 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. 1484
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or listings

    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
    455
    +0.02
    0.5%
    454
    +0.02
    0.5%
    573
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.02
    0.02
    669
    +0.02
    0.02
    84
    +0.02
    0.01
    Negative Logits
    uese
    -0.14
    wards
    -0.14
    elin
    -0.14
    igi
    -0.13
    gins
    -0.13
    jac
    -0.13
    pora
    -0.13
    eton
    -0.13
    dfx
    -0.12
    Led
    -0.12
    POSITIVE LOGITS
    BILITIES
    0.12
     Reflex
    0.11
    ¶ħ
    0.11
    ©¶æ¥µ
    0.10
    į
    0.10
     figured
    0.10
    ossal
    0.10
    Ī
    0.10
    Ĭ
    0.10
     Barnett
    0.10
    Activations Density 0.063%

    No Known Activations