© 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. 16537
    Prev
    Next
    INDEX
    Explanations

    quotations and reported speech

    oai_token-act-pair · gpt-3.5-turbo

    conclusive statements or sentiments that indicate an ending

    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
    ¥ŀ
    -0.84
     warr
    -0.77
     neighb
    -0.74
     citiz
    -0.73
    ģ«
    -0.70
     trave
    -0.68
     behavi
    -0.67
     inactive
    -0.67
     handc
    -0.67
     streng
    -0.66
    POSITIVE LOGITS
    âĢķ
    1.39
    —"
    1.35
    "âĢ¦
    1.25
    "—
    1.25
    "...
    1.22
    —
    1.18
    –
    1.10
    "'
    1.09
    -"
    1.09
    Wilson
    1.08
    Activations Density 0.152%

    No Known Activations