© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to exclusive access or privileges

    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
    288
    +0.16
    0.5%
    585
    +0.15
    0.5%
    656
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    585
    +0.16
    0.04
    288
    +0.15
    0.05
    568
    +0.15
    0.03
    Negative Logits
    olesterol
    -1.13
    apers
    -1.11
    ohan
    -1.11
    acter
    -1.08
    aper
    -1.07
    ako
    -1.07
    ;;;;;;;;;;;;
    -1.04
    orah
    -1.03
    idine
    -1.03
    udder
    -1.01
    POSITIVE LOGITS
     privileges
    1.07
    ities
    1.04
     rights
    1.02
     warr
    1.01
     exclusively
    0.99
    wcs
    0.98
     exclus
    0.96
    ITIES
    0.96
    ivity
    0.93
     reins
    0.93
    Activations Density 0.608%

    No Known Activations