© 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. 8-RES-JB
    11. 6389
    Prev
    Next
    INDEX
    Explanations

    communications about receiving and responding to messages or requests

    oai_token-act-pair · gpt-3.5-turbo

    instances of communication through emails and calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hene
    -0.70
    asonic
    -0.67
     dimensions
    -0.65
     independence
    -0.64
     restraints
    -0.63
    ATS
    -0.62
    strength
    -0.62
     duties
    -0.61
     Liberties
    -0.61
     autonomy
    -0.61
    POSITIVE LOGITS
     accidentally
    1.17
     mistakenly
    1.16
     unintentionally
    1.15
     wondering
    1.15
     inadvertently
    1.07
     falsely
    1.00
     wrongly
    1.00
     complaining
    0.99
     errone
    0.99
     incorrectly
    0.93
    Activations Density 0.913%

    No Known Activations