© 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. 1-RES-JB
    11. 20197
    Prev
    Next
    INDEX
    Explanations

    first-person expressions of personal opinions or preferences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or subjective statements

    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
     Meadow
    -0.84
     Clintons
    -0.67
     TED
    -0.67
     Roses
    -0.65
    iens
    -0.65
     Freeman
    -0.64
     Gulf
    -0.64
     Butter
    -0.63
     shadows
    -0.62
     Lim
    -0.61
    POSITIVE LOGITS
    Personally
    1.05
    etheless
    1.04
     Personally
    1.04
    odox
    0.92
    isSpecialOrderable
    0.83
     minded
    0.80
    cest
    0.77
     opin
    0.76
    ographically
    0.75
    wagen
    0.74
    Activations Density 0.006%

    No Known Activations