© 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. 8-RES-JB
    11. 20342
    Prev
    Next
    INDEX
    Explanations

    comparisons or statements involving similarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that compare or liken something to another thing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icious
    -0.76
    opian
    -0.68
     explor
    -0.67
    cffffcc
    -0.66
    isco
    -0.66
    iosyncr
    -0.66
    espie
    -0.66
    bid
    -0.65
    Returns
    -0.64
    endiary
    -0.64
    POSITIVE LOGITS
     usual
    0.82
     adults
    0.81
     normal
    0.77
     bandits
    0.76
     criminals
    0.76
     idiots
    0.73
     crazy
    0.72
     Ancients
    0.69
     Indians
    0.68
     Adults
    0.68
    Activations Density 0.142%

    No Known Activations