© 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. 4-RES-JB
    11. 10497
    Prev
    Next
    INDEX
    Explanations

    verbs related to providing evidence or proof

    oai_token-act-pair · gpt-3.5-turbo

    terms related to verification and authority

    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
    BOOK
    -0.80
     ACTION
    -0.74
    manship
    -0.69
     Enhancement
    -0.68
     Butt
    -0.67
    grass
    -0.67
    BALL
    -0.65
    terday
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
    ORGE
    -0.64
    POSITIVE LOGITS
    ated
    1.67
    ation
    1.66
    ating
    1.61
    ates
    1.37
    ations
    1.33
    ate
    1.31
    ators
    1.13
    ator
    1.10
    ited
    1.10
    ATED
    1.07
    Activations Density 0.057%

    No Known Activations