Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7739
    Prev
    Next
    INDEX
    Explanations

    specific formatting patterns in documents, specifically identified by colon followed by a digit number

    oai_token-act-pair · gpt-3.5-turbo

    colloquial or formatted expressions of code examples or structures

    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
     reservations
    -0.79
     tremend
    -0.78
     neighb
    -0.72
     reservation
    -0.71
     inspector
    -0.68
    hea
    -0.66
    odox
    -0.66
     investigator
    -0.66
     armed
    -0.65
     pamph
    -0.64
    POSITIVE LOGITS
     https
    1.16
     http
    1.11
    https
    1.03
    http
    0.99
     Logged
    0.95
     âĹı
    0.92
     namely
    0.86
     ie
    0.86
    ↵↵
    0.81
    <?
    0.81
    Activations Density 0.120%

    No Known Activations