© 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. 16806
    Prev
    Next
    INDEX
    Explanations

    mentions of specific actions related to eating

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "eat" and its variations

    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
     RC
    -0.72
     pol
    -0.67
     provisional
    -0.65
     licensed
    -0.65
     LinkedIn
    -0.64
     dem
    -0.64
     revision
    -0.64
     projects
    -0.64
     Bay
    -0.64
     downstream
    -0.62
    POSITIVE LOGITS
    eat
    4.91
    eating
    2.28
    Eat
    1.63
     Eat
    1.41
     eat
    1.29
    feat
    1.22
     eaten
    1.19
    ears
    1.09
    eal
    1.07
    eared
    1.06
    Activations Density 0.009%

    No Known Activations