© 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. 7615
    Prev
    Next
    INDEX
    Explanations

    phrases related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or processes involving interaction or alteration

    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
    War
    -0.69
    Shin
    -0.68
    Wall
    -0.67
     Wiz
    -0.66
     Okin
    -0.65
     Allied
    -0.63
     Winged
    -0.61
     Walton
    -0.61
    Image
    -0.60
     Wall
    -0.60
    POSITIVE LOGITS
    etheless
    0.98
    mosp
    0.89
    rontal
    0.87
    terday
    0.82
     UNIVERS
    0.78
    acters
    0.78
    ilogy
    0.78
    FTWARE
    0.77
    anwhile
    0.76
    ossibility
    0.73
    Activations Density 0.331%

    No Known Activations