© 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. 15466
    Prev
    Next
    INDEX
    Explanations

    references to news articles

    oai_token-act-pair · gpt-3.5-turbo

    indicators of a call to action or an invitation to read more

    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
    mbuds
    -0.71
     ours
    -0.67
     produ
    -0.65
     inspecting
    -0.64
     impuls
    -0.63
     headed
    -0.61
     leveled
    -0.61
     awa
    -0.61
     sanity
    -0.61
     theirs
    -0.60
    POSITIVE LOGITS
    than
    0.75
    Comments
    0.74
    Same
    0.72
    Prev
    0.71
    HB
    0.68
    SB
    0.68
    jri
    0.68
    ukong
    0.66
    Topics
    0.66
    ¨
    0.66
    Activations Density 0.042%

    No Known Activations