© 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. 0-RES-JB
    11. 1151
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or entities with the term "Prospect"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prospects and revisions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.78
    ifully
    -0.70
    doms
    -0.70
    HCR
    -0.69
    shr
    -0.69
    externalActionCode
    -0.69
    ciating
    -0.68
    baugh
    -0.67
    anguages
    -0.65
    iannopoulos
    -0.65
    POSITIVE LOGITS
     Prospect
    2.20
     revision
    1.46
    turned
    1.28
     dup
    1.12
     Dup
    1.07
     Huntington
    1.01
    bats
    1.01
     Method
    0.99
     Nost
    0.97
     upt
    0.97
    Activations Density 0.064%

    No Known Activations