© 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. 10-RES-JB
    11. 12134
    Prev
    Next
    INDEX
    Explanations

    strong personal traits or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal traits, attributes, and behavioral tendencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGHTS
    -0.81
    features
    -0.81
     maneuvers
    -0.80
    tics
    -0.80
    orks
    -0.78
    IDs
    -0.77
    results
    -0.77
     decorations
    -0.76
     extracts
    -0.75
     fixtures
    -0.75
    POSITIVE LOGITS
     whereby
    0.92
    atical
    0.89
     akin
    0.87
     standpoint
    0.86
     mentality
    0.83
     mindset
    0.79
     rethink
    0.77
     similar
    0.77
     conducive
    0.75
     analogous
    0.74
    Activations Density 0.261%

    No Known Activations