© 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. 15188
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rose" and its variations, indicating upward movement or increase

    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
    rolled
    -0.66
    portation
    -0.65
    pn
    -0.64
    oha
    -0.64
    ------------------------------------------------
    -0.64
    nered
    -0.62
    dp
    -0.62
    yssey
    -0.61
    RECT
    -0.60
    #$
    -0.60
    POSITIVE LOGITS
    ceed
    0.81
    xual
    0.79
    rising
    0.79
    mary
    0.76
    stairs
    0.75
    frog
    0.72
    ulic
    0.72
    water
    0.71
     tides
    0.69
    anqu
    0.68
    Activations Density 0.022%

    No Known Activations