© 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. 9-RES-JB
    11. 13287
    Prev
    Next
    INDEX
    Explanations

    financial and political terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with analysis and commentary, particularly relating to punditry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alph
    -0.64
     downt
    -0.63
     abusive
    -0.61
     sentiment
    -0.59
     cyn
    -0.59
     penetration
    -0.58
     browsing
    -0.57
     cinema
    -0.57
    USD
    -0.57
     predatory
    -0.56
    POSITIVE LOGITS
    itating
    1.25
    itant
    1.19
    itated
    1.15
    itations
    1.12
    ivably
    1.11
    itous
    1.10
    vable
    1.04
    ited
    1.02
    itates
    1.02
    ibly
    1.01
    Activations Density 0.091%

    No Known Activations