© 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. 24023
    Prev
    Next
    INDEX
    Explanations

    instances of capitalized words

    oai_token-act-pair · gpt-3.5-turbo

    statements that imply uncertainty or ambiguity

    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
    DI
    -0.78
    Jam
    -0.69
    FINEST
    -0.69
    Fac
    -0.69
    DCS
    -0.68
    urdue
    -0.68
     Brist
    -0.68
     Dupl
    -0.68
    onz
    -0.67
     Bridges
    -0.66
    POSITIVE LOGITS
    omb
    0.74
     metic
    0.73
     reconc
    0.69
     traged
    0.66
    omic
    0.66
     millenn
    0.65
     referen
    0.64
    umed
    0.63
     Machina
    0.63
     antioxid
    0.63
    Activations Density 0.000%

    No Known Activations