© 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. 6-RES-JB
    11. 13965
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "start with" followed by various topics or actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "start with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    span
    -0.79
    supported
    -0.73
    isSpecialOrderable
    -0.67
    stre
    -0.67
    agues
    -0.67
    abled
    -0.66
    soType
    -0.66
    hops
    -0.65
    zar
    -0.65
    late
    -0.65
    POSITIVE LOGITS
     scratch
    0.70
     introdu
    0.68
     obvious
    0.67
     respect
    0.67
     Ion
    0.65
     torches
    0.62
     tre
    0.60
     regard
    0.59
     Ronnie
    0.58
     breakfast
    0.58
    Activations Density 0.047%

    No Known Activations