© 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. 4-RES-JB
    11. 9202
    Prev
    Next
    INDEX
    Explanations

    autoantibodies or mentions related to auto conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to automobiles and automotive topics

    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
    ĸļ
    -1.12
    soever
    -0.92
     Flavoring
    -0.85
     GOODMAN
    -0.84
    redients
    -0.83
    swick
    -0.81
    enance
    -0.80
    ividual
    -0.80
    ewski
    -0.79
    arians
    -0.79
    POSITIVE LOGITS
    immune
    0.92
    cephal
    0.85
     autos
    0.77
     bailout
    0.76
     auto
    0.76
    actively
    0.75
     accident
    0.74
     transf
    0.73
    incre
    0.73
    exec
    0.72
    Activations Density 0.010%

    No Known Activations