© 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. 1-RES-JB
    11. 24236
    Prev
    Next
    INDEX
    Explanations

    things that are considered invalid or need to be invalidated

    oai_token-act-pair · gpt-3.5-turbo

    terms related to validity and invalidation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bio
    -0.78
    ILA
    -0.77
    illance
    -0.73
    Hat
    -0.71
    asio
    -0.70
    UTERS
    -0.69
    knit
    -0.68
    RH
    -0.68
    ynthesis
    -0.68
    bors
    -0.66
    POSITIVE LOGITS
     invalid
    1.11
    ating
    0.84
     unfocusedRange
    0.84
    ated
    0.78
     Invalid
    0.78
    Invalid
    0.72
     overwrite
    0.71
    ates
    0.68
    valid
    0.66
    ãĤ¹ãĥĪ
    0.66
    Activations Density 0.006%

    No Known Activations