© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13085
    Prev
    Next
    INDEX
    Explanations

    mentions of pieces or sections within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    references to "bits" 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
    ammad
    -0.78
    WAY
    -0.71
     SOS
    -0.68
     Physicians
    -0.62
    inated
    -0.62
     Predators
    -0.61
    NOR
    -0.61
    ordan
    -0.61
    INE
    -0.61
    ismo
    -0.61
    POSITIVE LOGITS
    terness
    0.96
     bits
    0.95
    meal
    0.94
    bits
    0.94
    wagon
    0.93
     Bits
    0.92
    cake
    0.87
    buck
    0.86
    umen
    0.86
    itives
    0.84
    Activations Density 0.011%

    No Known Activations