© 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. 11-RES-JB
    11. 21275
    Prev
    Next
    INDEX
    Explanations

    instances of determinations or firm decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing intent or determination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.80
    ENDED
    -0.77
    culated
    -0.71
    GoldMagikarp
    -0.70
    issance
    -0.68
     contrasted
    -0.65
    cius
    -0.65
    adj
    -0.65
    HD
    -0.64
    endi
    -0.63
    POSITIVE LOGITS
     tolerate
    1.32
     relent
    1.17
     hesitate
    1.13
     bud
    1.10
     bother
    1.05
     allow
    0.99
     forgive
    0.97
     let
    0.96
     EVER
    0.95
     condone
    0.94
    Activations Density 0.104%

    No Known Activations