© 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. 9-RES-JB
    11. 4883
    Prev
    Next
    INDEX
    Explanations

    paragraphs related to personal history or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of actions related to reading and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶
    -0.86
    etheless
    -0.83
    —
    -0.73
    )—
    -0.72
     Canaver
    -0.72
     nonetheless
    -0.71
    ,—
    -0.70
    "—
    -0.69
     GOODMAN
    -0.68
    .—
    -0.66
    POSITIVE LOGITS
     alot
    1.03
     doesnt
    0.86
     english
    0.84
     didnt
    0.80
     facebook
    0.80
     tho
    0.76
     thru
    0.75
     dont
    0.75
     whats
    0.71
     google
    0.70
    Activations Density 1.960%

    No Known Activations