© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23770
    Prev
    Next
    INDEX
    Explanations

    sentences containing phrases related to criticism or negative evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negative impacts or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gency
    -0.74
    ugu
    -0.73
    cu
    -0.71
    ory
    -0.69
    apter
    -0.69
     Closing
    -0.63
    uther
    -0.60
    monton
    -0.60
    gery
    -0.60
     veil
    -0.60
    POSITIVE LOGITS
     also
    0.96
     downright
    0.93
    also
    0.85
     ALSO
    0.83
     actively
    0.82
     secondly
    0.76
    Secondly
    0.76
     strategically
    0.73
    cially
    0.69
    DES
    0.69
    Activations Density 0.106%

    No Known Activations