© 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. 8-RES-JB
    11. 23540
    Prev
    Next
    INDEX
    Explanations

    information related to various activities or events happening in a wide range of topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of military training and geopolitical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    feld
    -0.51
    reason
    -0.50
    olitics
    -0.50
    revolution
    -0.49
    schild
    -0.49
    value
    -0.49
    hene
    -0.49
    tick
    -0.48
    democracy
    -0.47
    uberty
    -0.47
    POSITIVE LOGITS
    cellaneous
    0.59
    !:
    0.59
     Lastly
    0.55
    oother
    0.55
     Pastebin
    0.52
    iple
    0.52
     Discord
    0.51
     Assist
    0.49
    ossibility
    0.48
     standby
    0.48
    Activations Density 1.645%

    No Known Activations