© 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. 18577
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and statements

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists or phrases

    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
    ,
    -0.81
    ,...
    -0.75
    """
    -0.71
    SourceFile
    -0.71
    -
    -0.68
    !,
    -0.68
    vale
    -0.68
    Previous
    -0.67
    Wire
    -0.67
    Actor
    -0.67
    POSITIVE LOGITS
     somew
    0.69
     diminishing
    0.57
     rudimentary
    0.56
    stellar
    0.55
     tacit
    0.54
     nonexistent
    0.54
     incomplete
    0.53
    utenberg
    0.53
    ifiable
    0.52
     criminally
    0.52
    Activations Density 0.124%

    No Known Activations