© 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. 13134
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to specific topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning the existence or validity of certain entities or concepts

    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
    iliation
    -0.90
    icism
    -0.89
    cation
    -0.86
    matter
    -0.86
    terness
    -0.84
    leness
    -0.79
    analysis
    -0.76
    umption
    -0.75
    obook
    -0.74
    ossession
    -0.74
    POSITIVE LOGITS
     indications
    1.02
     moments
    0.93
     constants
    0.92
     nods
    0.92
     signs
    0.91
     contradictions
    0.91
     exceptions
    0.91
     differences
    0.90
     chances
    0.88
     keys
    0.88
    Activations Density 0.260%

    No Known Activations