© 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. 20440
    Prev
    Next
    INDEX
    Explanations

    lines of code that contain a return statement, with a strong preference for those that return a value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the keyword "return" in programming 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
    Cola
    -0.88
    ussen
    -0.76
    cffff
    -0.72
    icago
    -0.71
    habi
    -0.71
    oshop
    -0.70
     disse
    -0.70
    itcher
    -0.70
    insula
    -0.69
    keley
    -0.68
    POSITIVE LOGITS
    ees
    0.81
     Returns
    0.80
     Return
    0.71
     TRUE
    0.68
    Returns
    0.67
    ports
    0.66
    nil
    0.65
    ported
    0.65
     Values
    0.64
     Democr
    0.64
    Activations Density 0.016%

    No Known Activations