© 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. 7572
    Prev
    Next
    INDEX
    Explanations

    verbs related to activism or organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mobilization and group action

    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
    ©¶æ
    -0.71
    ibble
    -0.68
     tasting
    -0.64
    fixed
    -0.63
    abyte
    -0.61
    obar
    -0.59
     bye
    -0.59
     autopsy
    -0.58
    birth
    -0.58
    atto
    -0.58
    POSITIVE LOGITS
    andise
    0.90
     mobilization
    0.88
     volunteers
    0.82
     mobs
    0.79
     mobilized
    0.79
    roup
    0.78
     mobilize
    0.78
    izational
    0.77
     masses
    0.74
    eer
    0.74
    Activations Density 0.122%

    No Known Activations