© 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. 9-RES-JB
    11. 999
    Prev
    Next
    INDEX
    Explanations

    submissions of documents or pieces of writing

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of a specific formatted token or marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cors
    -0.67
    agne
    -0.67
     Papers
    -0.66
    ATHER
    -0.66
     wool
    -0.65
    OPLE
    -0.65
     Hammer
    -0.65
     wings
    -0.64
     Royale
    -0.64
     fet
    -0.64
    POSITIVE LOGITS
    sequent
    1.67
    sequently
    1.66
    mitted
    1.60
    stantial
    1.60
    scription
    1.43
    stant
    1.40
    ordinate
    1.37
    verting
    1.31
    mitting
    1.31
    versive
    1.27
    Activations Density 0.027%

    No Known Activations