© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9697
    Prev
    Next
    INDEX
    Explanations

    specific, detailed information

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "details" or related terms indicating important information or specifics

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

    No Comments

    Negative Logits
    ammers
    -0.75
    nder
    -0.72
    azar
    -0.72
    asus
    -0.68
    obos
    -0.66
    own
    -0.64
    ony
    -0.64
    SW
    -0.63
    ONY
    -0.63
    sw
    -0.63
    POSITIVE LOGITS
     details
    1.12
     detail
    1.01
    displayText
    0.86
     specifics
    0.84
     Details
    0.82
     particulars
    0.78
    bourg
    0.78
    details
    0.78
     wording
    0.77
     glean
    0.76
    Activations Density 0.024%

    No Known Activations