© 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. 8274
    Prev
    Next
    INDEX
    Explanations

    terms related to specific body parts (horseshoe and fuselage)

    oai_token-act-pair · gpt-3.5-turbo
    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
    OWS
    -0.71
    Measure
    -0.69
    Water
    -0.69
     Beaut
    -0.69
     Debt
    -0.69
    endor
    -0.68
     Sacrament
    -0.67
    Words
    -0.67
    lust
    -0.67
    ãĥ´ãĤ¡
    -0.67
    POSITIVE LOGITS
    £ı
    0.85
    pperc
    0.83
     haw
    0.82
    esh
    0.78
     jo
    0.70
    Ĵ
    0.69
     whip
    0.68
    cffff
    0.68
     hors
    0.68
    etooth
    0.67
    Activations Density 0.014%

    No Known Activations