© 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. 8-RES-JB
    11. 10483
    Prev
    Next
    INDEX
    Explanations

    terms related to recent events, reports, or research

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifier
    -0.81
    iest
    -0.74
    onto
    -0.73
    keleton
    -0.70
    artment
    -0.70
    estamp
    -0.69
    ressor
    -0.69
    ouf
    -0.69
    iphate
    -0.69
    essee
    -0.69
    POSITIVE LOGITS
     circumstances
    1.33
     assumptions
    1.20
     considerations
    1.19
     trends
    1.15
     expectations
    1.13
     developments
    1.09
     constraints
    1.08
     interpretations
    1.06
     indications
    1.06
     efforts
    1.06
    Activations Density 0.422%

    No Known Activations