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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 13057
    Prev
    Next
    INDEX
    Explanations

    keywords related to coming together in support or protest

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rally" and its variations in contexts related to gathering or organizing support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.66
    rences
    -0.66
     Dictionary
    -0.64
     retrospective
    -0.64
    roma
    -0.64
    gins
    -0.63
    QB
    -0.61
    secution
    -0.61
    ternity
    -0.61
    missions
    -0.61
    POSITIVE LOGITS
    andise
    1.11
    arity
    0.78
    isers
    0.77
    steen
    0.76
     against
    0.76
    iser
    0.75
     Against
    0.73
    roup
    0.72
     GOODMAN
    0.72
    itud
    0.71
    Activations Density 0.070%

    No Known Activations