© 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. 13433
    Prev
    Next
    INDEX
    Explanations

    phrases related to allowing or enabling something

    oai_token-act-pair · gpt-3.5-turbo

    references to capabilities and permissions within various contexts

    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
     Lump
    -0.66
    govtrack
    -0.64
     Notting
    -0.61
    olate
    -0.60
    onday
    -0.59
    ĪĴ
    -0.58
    TED
    -0.58
    ravis
    -0.57
    é¾įå¥ij士
    -0.57
     Jindal
    -0.56
    POSITIVE LOGITS
     access
    0.80
     unrestricted
    0.80
     flexibility
    0.79
     freely
    0.77
     deduction
    0.74
    SpaceEngineers
    0.71
    tera
    0.71
     lapse
    0.70
     slip
    0.70
    parency
    0.70
    Activations Density 0.213%

    No Known Activations