© 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. 8-RES-JB
    11. 20177
    Prev
    Next
    INDEX
    Explanations

    descriptions of experiencing something physically

    oai_token-act-pair · gpt-3.5-turbo

    instances of experiencing or tasting new things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blaming
    -0.85
    redict
    -0.69
     citing
    -0.68
    ItemImage
    -0.67
     refrain
    -0.67
     refusing
    -0.67
     claiming
    -0.67
    advertising
    -0.66
     blamed
    -0.64
     comprom
    -0.64
    POSITIVE LOGITS
     firsthand
    1.31
     glimps
    0.84
     prototypes
    0.84
     demos
    0.83
     preview
    0.78
     scenery
    0.78
     whats
    0.77
     majesty
    0.77
     goodies
    0.73
     glimpse
    0.73
    Activations Density 0.406%

    No Known Activations