© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    terms related to forensic investigations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to forensic investigations

    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
    unin
    -1.02
    yip
    -0.91
     Huck
    -0.73
    Spoiler
    -0.72
    idays
    -0.72
    downs
    -0.70
    cair
    -0.70
    ional
    -0.68
    bid
    -0.66
    spring
    -0.66
    POSITIVE LOGITS
     examination
    0.92
    nsic
    0.92
    nsics
    0.90
    abilia
    0.85
     examinations
    0.83
     analysis
    0.81
     evaluation
    0.81
     Examination
    0.78
     pathology
    0.78
     laboratories
    0.78
    Activations Density 0.029%

    No Known Activations