© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3190
    Prev
    Next
    INDEX
    Explanations

    pronouns 'his' or 'her' followed by possessive or descriptive words

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their associated attributes or roles

    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
    ÑĮ
    -0.84
    Reviewed
    -0.78
    agues
    -0.77
    isode
    -0.74
    vier
    -0.73
    oke
    -0.73
    cells
    -0.73
    akings
    -0.72
    itutes
    -0.72
    okes
    -0.71
    POSITIVE LOGITS
     penchant
    1.65
     inability
    1.53
     propensity
    1.49
     tendency
    1.45
     willingness
    1.44
     insistence
    1.42
     unwillingness
    1.38
     refusal
    1.38
     reluctance
    1.27
     obsession
    1.27
    Activations Density 0.242%

    No Known Activations