© 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. 6121
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and entities involved in controversies or scandals

    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
    asha
    -0.82
    taboola
    -0.74
    gra
    -0.71
    aten
    -0.69
    uffle
    -0.68
    lander
    -0.68
    ilde
    -0.65
     Cosponsors
    -0.64
    iba
    -0.63
    atre
    -0.62
    POSITIVE LOGITS
     permission
    0.93
     pause
    0.78
     ample
    0.73
     thumbs
    0.71
     plenty
    0.70
     access
    0.69
    ample
    0.68
     valuable
    0.67
     nightmares
    0.64
     congratulations
    0.64
    Activations Density 0.326%

    No Known Activations