© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 16350
    Prev
    Next
    INDEX
    Explanations

    terms related to skills, knowledge, and credibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to performance and capability metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nings
    -0.79
    cies
    -0.77
    urations
    -0.75
    ness
    -0.74
    paces
    -0.72
    thus
    -0.69
    itudes
    -0.69
    enance
    -0.68
    than
    -0.68
    itude
    -0.68
    POSITIVE LOGITS
     enh
    1.01
    less
    0.96
     elim
    0.84
     enhancing
    0.84
     booster
    0.84
     advoc
    0.83
     builder
    0.83
     seeker
    0.83
     oriented
    0.82
     seekers
    0.81
    Activations Density 0.502%

    No Known Activations