© 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. 10-RES-JB
    11. 21754
    Prev
    Next
    INDEX
    Explanations

    actions related to logging in, signing in, or being sworn in

    oai_token-act-pair · gpt-3.5-turbo

    actions related to logging into or out of accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hem
    -0.62
    heid
    -0.59
     Parables
    -0.56
    arel
    -0.55
    duc
    -0.53
    sein
    -0.52
     Centauri
    -0.52
    conserv
    -0.52
     ¶
    -0.51
     ende
    -0.51
    POSITIVE LOGITS
     into
    1.20
     INTO
    1.00
    into
    0.97
     onto
    0.96
     Into
    0.93
     horns
    0.86
     onward
    0.84
    imentary
    0.78
     onwards
    0.75
    MpServer
    0.74
    Activations Density 0.315%

    No Known Activations