© 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. 2640
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of pushing boundaries or limits is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating limits or boundaries related to various concepts

    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
     istg
    -0.54
    ucci
    -0.47
     Unsure
    -0.42
    few
    -0.42
    wcs
    -0.41
    =]
    -0.40
    uristic
    -0.39
    oult
    -0.39
    .''.
    -0.38
    eday
    -0.38
    POSITIVE LOGITS
     ours
    0.56
     our
    0.55
     sorts
    0.55
     course
    0.53
     these
    0.49
     JUSTICE
    0.49
     the
    0.47
     theirs
    0.47
     each
    0.46
     their
    0.45
    Activations Density 0.527%

    No Known Activations