© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1882
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where something is lacking or missing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "no."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAFT
    -0.71
    midt
    -0.66
    ean
    -0.66
    mire
    -0.65
    lus
    -0.64
    thouse
    -0.63
    rex
    -0.62
    aly
    -0.62
    nesium
    -0.62
    inarily
    -0.60
    POSITIVE LOGITS
    xious
    1.20
     measurable
    0.93
     meaningful
    0.93
     detectable
    0.91
     discern
    0.90
    except
    0.89
     doubt
    0.88
     longer
    0.88
     shortage
    0.87
    onday
    0.86
    Activations Density 0.095%

    No Known Activations