© 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. 7-RES-JB
    11. 17171
    Prev
    Next
    INDEX
    Explanations

    references to a specific term or entity represented by "ED" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to Electronic Dance music (EDM)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auga
    -0.75
    atom
    -0.74
    hold
    -0.71
    quote
    -0.67
    urers
    -0.67
    ieri
    -0.67
    quit
    -0.67
    cha
    -0.66
    keye
    -0.66
    ãĤ¨ãĥ«
    -0.65
    POSITIVE LOGITS
    LES
    1.16
    EN
    1.11
    GE
    1.10
    IZ
    1.10
    IED
    1.09
    IA
    1.08
    LAND
    1.08
    LE
    1.07
    IST
    1.07
    IC
    1.07
    Activations Density 0.058%

    No Known Activations