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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 1985
    Prev
    Next
    INDEX
    Explanations

    instances of words related to commands, orders, or strong desires

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "will" and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.80
    aughed
    -0.71
    orget
    -0.68
    ĻĤ
    -0.68
    acl
    -0.64
    english
    -0.64
    Reporting
    -0.64
     Composite
    -0.60
     Mahjong
    -0.60
     certific
    -0.60
    POSITIVE LOGITS
    fulness
    0.97
    FUL
    0.89
    sburg
    0.84
    power
    0.82
    lessness
    0.76
    ows
    0.74
    igent
    0.74
    ful
    0.73
    orial
    0.72
    ies
    0.71
    Activations Density 0.064%

    No Known Activations