© 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. 1-RES-JB
    11. 17966
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts, particularly the neck

    oai_token-act-pair · gpt-3.5-turbo

    references to the neck

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.70
    ña
    -0.65
     Soy
    -0.63
    PLIED
    -0.62
    Avg
    -0.60
    ========
    -0.59
    ILE
    -0.58
     Flavoring
    -0.58
    created
    -0.57
    effective
    -0.57
    POSITIVE LOGITS
     neck
    1.22
    lace
    1.20
     necks
    1.13
    beard
    1.09
    tie
    1.04
    bones
    1.03
    bone
    1.03
     throat
    0.96
     Neck
    0.91
    bridge
    0.91
    Activations Density 0.004%

    No Known Activations