© 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. 0-RES-JB
    11. 9944
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities, likely related to rankings or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to overall assessments or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Suppose
    -0.69
    aband
    -0.67
    ZE
    -0.64
    lish
    -0.63
     Protest
    -0.61
    Lago
    -0.60
     fools
    -0.58
    legram
    -0.58
    lic
    -0.57
    Submit
    -0.57
    POSITIVE LOGITS
     overall
    3.63
     Overall
    2.35
    Overall
    2.14
     overarching
    1.45
     total
    1.43
     general
    1.21
     outright
    1.20
     underlying
    1.12
     aggregate
    1.10
     broader
    1.08
    Activations Density 0.009%

    No Known Activations