© 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. 4-RES-JB
    11. 17018
    Prev
    Next
    INDEX
    Explanations

    phrases related to evidence analysis and discussion

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Evidence

    No Comments

    Negative Logits
    quer
    -0.71
     throats
    -0.71
    otom
    -0.69
    jug
    -0.69
    cer
    -0.66
    skill
    -0.66
    ategory
    -0.65
    ttle
    -0.65
    cise
    -0.63
    Hop
    -0.61
    POSITIVE LOGITS
     evidence
    0.98
    evidence
    0.96
    Evidence
    0.94
     Evidence
    0.90
    fulness
    0.77
    orial
    0.76
     suggests
    0.76
     evid
    0.75
     validity
    0.75
    proof
    0.75
    Activations Density 0.023%

    No Known Activations