© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7105
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical appearance that signify thinness or smallness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "slim."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citation
    -0.77
    DCS
    -0.70
     Watching
    -0.70
    NAT
    -0.69
     Abuse
    -0.67
     Nationwide
    -0.64
    CRE
    -0.64
     Homeland
    -0.63
    ————————————————
    -0.63
     Trials
    -0.63
    POSITIVE LOGITS
    ming
    1.09
    med
    0.96
    tty
    0.85
    ethy
    0.82
    pling
    0.82
     slim
    0.81
    ples
    0.81
    psons
    0.80
    nir
    0.79
    ply
    0.78
    Activations Density 0.007%

    No Known Activations