© 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. 20416
    Prev
    Next
    INDEX
    Explanations

    words related to genetics and inheritance

    oai_token-act-pair · gpt-3.5-turbo

    the possessive form of "it."

    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
     scar
    -0.66
     cuff
    -0.65
     possible
    -0.63
     handc
    -0.61
    croft
    -0.61
     relief
    -0.61
     discouraged
    -0.60
     Colo
    -0.59
     foil
    -0.59
     challenge
    -0.58
    POSITIVE LOGITS
    its
    4.44
    ITS
    2.72
    itted
    2.08
    it
    1.94
    iting
    1.94
    ited
    1.90
    itting
    1.81
    itors
    1.53
    IT
    1.53
    Its
    1.49
    Activations Density 0.006%

    No Known Activations