© 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. 2-RES-JB
    11. 4335
    Prev
    Next
    INDEX
    Explanations

    the word "extract" with a high activation value, suggesting a focus on extraction or removal processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "extract" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Die
    -0.78
    nd
    -0.74
    die
    -0.74
    early
    -0.71
    cas
    -0.69
     Gry
    -0.64
    wn
    -0.63
    stand
    -0.63
    present
    -0.62
    gaard
    -0.62
    POSITIVE LOGITS
     extract
    1.17
     extracted
    1.06
     extracting
    0.97
     extracts
    0.96
     Extract
    0.95
     extraction
    0.91
    ivist
    0.88
    ions
    0.83
    ractor
    0.83
    racted
    0.83
    Activations Density 0.011%

    No Known Activations