© 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. 10059
    Prev
    Next
    INDEX
    Explanations

    words related to deviation or straying from a certain path or norm

    oai_token-act-pair · gpt-3.5-turbo

    words related to deviations or variations from a norm

    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
    ingham
    -0.69
    mel
    -0.67
    tu
    -0.64
     Tess
    -0.64
    onna
    -0.63
    д
    -0.63
    amaz
    -0.63
    bring
    -0.62
    gel
    -0.61
     Melania
    -0.60
    POSITIVE LOGITS
    adoes
    0.80
    odox
    0.77
     tendencies
    0.74
     erratic
    0.71
     departure
    0.70
    veyard
    0.70
    untled
    0.69
     diver
    0.68
    ollow
    0.67
     divergence
    0.67
    Activations Density 0.060%

    No Known Activations