© 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. 21445
    Prev
    Next
    INDEX
    Explanations

    informational parts separated by formatting elements such as special characters, likely to focus on queries or descriptions in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    questions and prompts that initiate discussions or topics

    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
     eleph
    -1.01
     proport
    -0.83
    anwhile
    -0.82
    aditional
    -0.79
     looph
    -0.72
     helicop
    -0.71
     princ
    -0.70
     mathemat
    -0.70
     exting
    -0.69
    Þ
    -0.67
    POSITIVE LOGITS
    Answer
    1.09
    ↵
    0.87
    Redd
    0.78
    DH
    0.75
    Honestly
    0.75
    RH
    0.74
    Absolutely
    0.73
    Rh
    0.72
    Well
    0.71
    MI
    0.71
    Activations Density 0.163%

    No Known Activations