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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8000
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific demographics or groups of people

    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
    ggles
    -0.72
     Sierra
    -0.70
    iage
    -0.67
     Flavoring
    -0.66
    ibus
    -0.65
     foregoing
    -0.65
    insula
    -0.63
    ventory
    -0.60
    robe
    -0.60
    ederal
    -0.59
    POSITIVE LOGITS
    arily
    0.85
    worthy
    0.80
    isible
    0.80
    urated
    0.79
    irable
    0.78
    ivable
    0.76
    opped
    0.76
    omorphic
    0.75
    enced
    0.74
    alysed
    0.74
    Activations Density 0.600%

    No Known Activations