© 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. 9-RES-JB
    11. 2438
    Prev
    Next
    INDEX
    Explanations

    words related to elements of the periodic table or chemical compounds

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roots
    -0.70
    staking
    -0.66
    tsky
    -0.63
    jriwal
    -0.62
    ngth
    -0.61
    bane
    -0.60
     rooting
    -0.59
    Downloadha
    -0.59
    fully
    -0.59
     upside
    -0.55
    POSITIVE LOGITS
    ement
    0.89
    Allah
    0.84
    amara
    0.82
    ova
    0.79
    OVA
    0.72
    ect
    0.70
    ®
    0.68
    illas
    0.68
    uers
    0.67
    oa
    0.67
    Activations Density 0.208%

    No Known Activations