© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1879
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or desires

    oai_token-act-pair · gpt-3.5-turbo

    themes related to sexuality and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.51
    çīĪ
    -0.47
    ãĥ´
    -0.47
    ofi
    -0.44
    anwhile
    -0.42
     accum
    -0.42
     cumulative
    -0.41
     referen
    -0.41
     declarations
    -0.40
     Niet
    -0.40
    POSITIVE LOGITS
     anymore
    0.66
     ASAP
    0.65
     someday
    0.64
     sooner
    0.62
    ?ãĢį
    0.59
    ?",
    0.59
    ?".
    0.58
     Belfast
    0.58
    ?
    0.58
    ?'
    0.56
    Activations Density 1.440%

    No Known Activations