© 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. 17159
    Prev
    Next
    INDEX
    Explanations

    verb phrases indicating verification or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating confirmation or acknowledgment of information

    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
    à¦
    -0.76
     ILCS
    -0.75
    ISA
    -0.70
    à
    -0.70
    iac
    -0.69
    è
    -0.68
    scribe
    -0.67
    ene
    -0.66
    isible
    -0.64
    board
    -0.64
    POSITIVE LOGITS
    WER
    0.73
     NX
    0.72
     Wednesday
    0.70
     Tuesday
    0.70
    rists
    0.70
     afterward
    0.70
     that
    0.68
     disclosing
    0.68
     anecd
    0.67
     difficulties
    0.67
    Activations Density 0.210%

    No Known Activations