© 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. 2-RES-JB
    11. 11295
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially last names

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "igan," indicating a focus on certain names or terms associated with specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newsp
    -0.76
     tradem
    -0.65
    ngth
    -0.65
    dates
    -0.64
    nesday
    -0.64
    grading
    -0.63
     mold
    -0.63
    lict
    -0.62
     Gemini
    -0.62
     spaced
    -0.61
    POSITIVE LOGITS
    igans
    1.86
    igan
    1.74
    dale
    0.94
    keye
    0.92
    ieri
    0.86
     Nights
    0.82
    enburg
    0.81
    osity
    0.80
    owski
    0.80
    omics
    0.80
    Activations Density 0.010%

    No Known Activations