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. 17384
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or occurrences happening for the first time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant first occurrences or milestones

    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
    otto
    -0.68
    CHAT
    -0.66
    ourt
    -0.65
    asty
    -0.65
    ramid
    -0.61
    ote
    -0.60
     tomat
    -0.59
    riad
    -0.58
    rib
    -0.57
    ophe
    -0.57
    POSITIVE LOGITS
    imester
    0.79
     Ago
    0.76
    brates
    0.76
    frames
    0.73
     anniversary
    0.70
     horizon
    0.67
    teness
    0.67
    period
    0.66
    worldly
    0.65
    abl
    0.63
    Activations Density 0.023%

    No Known Activations