© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6219
    Prev
    Next
    INDEX
    Explanations

    words related to actions happening before something else

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "pre-" 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
     Tuls
    -0.86
    BuyableInstoreAndOnline
    -0.81
    isSpecialOrderable
    -0.76
     Shard
    -0.73
     Violet
    -0.73
    estones
    -0.72
    edge
    -0.72
    soType
    -0.72
    tons
    -0.71
    wagen
    -0.70
    POSITIVE LOGITS
     pre
    3.24
     Pre
    2.33
    Pre
    1.93
    pre
    1.75
     PRE
    1.64
     prec
    1.63
     prep
    1.54
     prem
    1.47
     pred
    1.43
    PRE
    1.40
    Activations Density 0.010%

    No Known Activations