© 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. 12601
    Prev
    Next
    INDEX
    Explanations

    phrases related to advancement and forward-thinking

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to forward-thinking and planning

    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
    soDeliveryDate
    -0.73
    ucket
    -0.72
    seys
    -0.69
    Hour
    -0.67
    bath
    -0.66
    fresh
    -0.66
    ById
    -0.66
    minus
    -0.65
    chens
    -0.65
    Gi
    -0.65
    POSITIVE LOGITS
    enment
    0.94
     advancement
    0.73
     fray
    0.73
    enium
    0.72
     motions
    0.72
     rall
    0.67
    hement
    0.67
    mire
    0.65
     Conversation
    0.65
     viewpoints
    0.63
    Activations Density 0.127%

    No Known Activations