© 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. 4-RES-JB
    11. 22130
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to movies or physical locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fall" in various contexts

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

    No Comments

    Negative Logits
    other
    -0.66
    cius
    -0.66
    chedel
    -0.65
     horn
    -0.63
    PLA
    -0.59
     CLSID
    -0.57
    cffff
    -0.57
     skilled
    -0.57
     sshd
    -0.57
     micro
    -0.56
    POSITIVE LOGITS
    opian
    1.10
    falls
    1.05
    fall
    0.97
    owship
    0.84
    ibility
    0.83
    atio
    0.81
    ãĤ£
    0.80
    acies
    0.79
    furt
    0.77
    orage
    0.76
    Activations Density 0.015%

    No Known Activations