© 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. 14296
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of being bound or limited is mentioned

    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
    370
    +0.22
    0.7%
    326
    +0.17
    0.5%
    546
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.22
    0.07
    288
    +0.17
    0.08
    346
    +0.16
    0.04
    Negative Logits
    issance
    -1.28
    zanne
    -1.03
    amera
    -1.01
    dfx
    -1.01
    HAEL
    -1.01
    ortmund
    -1.01
    overed
    -0.99
    akura
    -0.99
    onductor
    -0.98
    oples
    -0.97
    POSITIVE LOGITS
    sym
    1.55
    less
    1.47
    ging
    1.37
     bound
    1.37
    binding
    1.36
    lessly
    1.30
    fold
    1.25
    pipe
    1.20
    lock
    1.19
    ingly
    1.18
    Activations Density 1.184%

    No Known Activations