© 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 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. 12151
    Prev
    Next
    INDEX
    Explanations

    phrases related to time sequences

    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
    472
    +0.16
    0.5%
    183
    +0.14
    0.5%
    240
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.16
    0.03
    472
    +0.14
    0.02
    5
    +0.14
    0.02
    Negative Logits
    atives
    -1.11
    senal
    -1.07
    ativity
    -1.04
    İĭ
    -1.01
    pel
    -0.98
    ò
    -0.93
    BIP
    -0.93
    umbai
    -0.89
    iosyncr
    -0.89
    HCR
    -0.89
    POSITIVE LOGITS
    aneously
    1.25
     thereafter
    1.08
    theless
    1.03
    idious
    1.01
     realised
    0.97
    ifiable
    0.91
     afterwards
    0.91
    thing
    0.88
     lear
    0.88
     realized
    0.88
    Activations Density 0.154%

    No Known Activations