© 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. 22560
    Prev
    Next
    INDEX
    Explanations

    statistics related to changes over time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "from" in various contexts

    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
     mirrors
    -0.68
    fights
    -0.65
    anners
    -0.65
    Admin
    -0.64
    awar
    -0.62
    colo
    -0.61
    rive
    -0.58
     FTA
    -0.57
    insk
    -0.57
    igent
    -0.56
    POSITIVE LOGITS
     customary
    0.77
    ivalent
    0.70
     usual
    0.69
     37
    0.68
     52
    0.67
     33
    0.67
     38
    0.65
    ãĥĩãĤ£
    0.65
     39
    0.65
     32
    0.64
    Activations Density 0.100%

    No Known Activations