© 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. 7-RES-JB
    11. 17765
    Prev
    Next
    INDEX
    Explanations

    terms related to openness or access

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "open."

    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
    iage
    -0.72
    ibur
    -0.70
    uke
    -0.62
    ulk
    -0.61
    UTE
    -0.61
     Chemistry
    -0.60
     Cock
    -0.59
     Bots
    -0.59
     Bog
    -0.59
     Claw
    -0.59
    POSITIVE LOGITS
     indefinitely
    0.79
     minded
    0.78
    hearted
    0.76
    iltr
    0.75
    erness
    0.73
    going
    0.72
    open
    0.71
     eyed
    0.71
    heartedly
    0.71
     unrestricted
    0.70
    Activations Density 0.042%

    No Known Activations