© 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. 801
    Prev
    Next
    INDEX
    Explanations

    quantities or numbers of items

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of quantity descriptors

    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
    Constructed
    -0.74
    istan
    -0.72
    ESE
    -0.71
    heter
    -0.67
    someone
    -0.67
    existent
    -0.66
    they
    -0.65
    unless
    -0.65
    ARY
    -0.65
    ensis
    -0.65
    POSITIVE LOGITS
     interesting
    0.85
     accol
    0.83
     exciting
    0.82
     advantages
    0.79
     surprises
    0.78
     milestones
    0.78
     enhancements
    0.77
     fascinating
    0.77
     unanswered
    0.76
     improvements
    0.75
    Activations Density 0.252%

    No Known Activations