© 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. 7-RES-JB
    11. 11625
    Prev
    Next
    INDEX
    Explanations

    characters and actions enclosed in square brackets

    oai_token-act-pair · gpt-3.5-turbo

    closing or opening brackets and certain punctuation marks used in dialogue

    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
    -+-+
    -0.76
    zh
    -0.73
    ĸļ
    -0.72
    ãĥł
    -0.70
    ĪĴ
    -0.69
    chen
    -0.68
    İĭ
    -0.67
    zb
    -0.66
    ãĤ¢ãĥ«
    -0.66
    ij
    -0.66
    POSITIVE LOGITS
    selves
    0.74
    },"
    0.65
     ,"
    0.64
    indust
    0.61
    station
    0.58
    shall
    0.57
     Mol
    0.57
    football
    0.57
     waiver
    0.57
    thumbnails
    0.55
    Activations Density 0.051%

    No Known Activations