© 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. 0-RES-JB
    11. 22227
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to punishment or consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal punishments or offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cantor
    -0.71
    ependence
    -0.71
    ogg
    -0.70
     Organ
    -0.65
    ummer
    -0.64
     Consulting
    -0.64
     omn
    -0.64
     Wells
    -0.63
    arger
    -0.63
    helle
    -0.63
    POSITIVE LOGITS
     punishable
    3.78
    ailable
    1.17
    vable
    1.09
    achable
    1.07
     bordering
    1.05
     misdem
    1.01
     awaited
    0.93
     laughable
    0.92
     payable
    0.92
    ceivable
    0.91
    Activations Density 0.050%

    No Known Activations