Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17325
    Prev
    Next
    INDEX
    Explanations

    mentions of "first" occurrences or events within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    key events or notable occurrences

    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
     abound
    -0.76
    tnc
    -0.64
    ruciating
    -0.58
     Maxim
    -0.57
    cdn
    -0.57
     Spears
    -0.57
     unfocusedRange
    -0.57
    ĺħ
    -0.57
     Preservation
    -0.57
    =-=-=-=-
    -0.57
    POSITIVE LOGITS
     outing
    0.77
     imaginable
    0.75
     arrives
    0.74
     hurdle
    0.73
    imester
    0.73
     foray
    0.71
    hander
    0.66
    baugh
    0.66
     hatch
    0.65
    nesday
    0.64
    Activations Density 0.415%

    No Known Activations