© 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. 23289
    Prev
    Next
    INDEX
    Explanations

    sections related to attributions or additional information in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    frequently used punctuation marks, specifically brackets and commas

    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
     antioxid
    -0.71
    eton
    -0.68
    iners
    -0.64
    arettes
    -0.64
     seams
    -0.61
     Releases
    -0.61
    ļéĨĴ
    -0.61
     Excellence
    -0.60
    ãĥ¼ãĥ³
    -0.59
    alez
    -0.59
    POSITIVE LOGITS
    ...]
    1.26
    Pg
    1.24
    note
    1.18
    âĢ¦]
    1.12
    Footnote
    1.09
    ?]
    0.93
    :]
    0.92
    sic
    0.92
    src
    0.87
    RFC
    0.79
    Activations Density 0.025%

    No Known Activations