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

    Neuronpedia

    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. 11004
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone speaking

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific individual or speaker

    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
    noon
    -0.73
    etheless
    -0.68
     interfering
    -0.63
    cious
    -0.63
    rocket
    -0.62
     totality
    -0.59
    selection
    -0.59
     caliber
    -0.59
    acters
    -0.58
     Treaty
    -0.57
    POSITIVE LOGITS
     said
    1.25
     wrote
    1.19
     joked
    1.13
     says
    1.10
     tweeted
    1.08
     explained
    1.04
     told
    1.03
     exclaimed
    1.03
    said
    0.98
    'd
    0.96
    Activations Density 0.062%

    No Known Activations