© 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. 4-RES-JB
    6. 381
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames and online handles

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters, some of which may represent non-standard or encoded text

    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
    ardless
    -0.61
    achev
    -0.56
    ONSORED
    -0.53
    idated
    -0.51
    UME
    -0.49
    ierre
    -0.48
     elim
    -0.48
    ikuman
    -0.47
    arsity
    -0.45
    auntlet
    -0.45
    POSITIVE LOGITS
    SEE
    0.46
     gran
    0.45
    media
    0.44
     Cly
    0.42
     ke
    0.42
     helpless
    0.39
     gib
    0.39
    cond
    0.39
    bors
    0.39
    ministic
    0.39
    Activations Density 2.074%

    No Known Activations