© 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. 4-RES-JB
    11. 10334
    Prev
    Next
    INDEX
    Explanations

    verbs related to appreciation or recognition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to appreciation and retaliation

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

    No Comments

    Negative Logits
     Doctrine
    -0.77
    WAYS
    -0.77
    dress
    -0.73
     Origin
    -0.71
     LORD
    -0.71
    manship
    -0.70
     Dragonbound
    -0.70
     Principle
    -0.69
     Belt
    -0.68
    IELD
    -0.66
    POSITIVE LOGITS
    ators
    1.67
    ating
    1.67
    ator
    1.59
    ational
    1.57
    ative
    1.46
    ations
    1.46
    atively
    1.45
    ated
    1.45
    ates
    1.38
    atory
    1.34
    Activations Density 0.044%

    No Known Activations