© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10762
    Prev
    Next
    INDEX
    Explanations

    words related to accidental mistakes or errors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slip" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.67
    è¦ļéĨĴ
    -0.64
    inction
    -0.64
    nea
    -0.61
    rior
    -0.59
    ============
    -0.58
    uliffe
    -0.58
    ricular
    -0.57
    bell
    -0.57
    native
    -0.56
    POSITIVE LOGITS
     slip
    0.89
    stream
    0.83
    weed
    0.81
    bilt
    0.79
    opolis
    0.79
     slips
    0.77
    cover
    0.76
    ibrary
    0.76
     Whedon
    0.74
    uten
    0.74
    Activations Density 0.009%

    No Known Activations