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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16780
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with a significant event or impactful statement

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey statistical information or numerical data

    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
     scenery
    -0.84
     expl
    -0.71
     fishes
    -0.69
     everywhere
    -0.68
     sleeve
    -0.66
     ourselves
    -0.66
    itably
    -0.65
     heterogeneity
    -0.64
     metab
    -0.63
     minion
    -0.63
    POSITIVE LOGITS
     Earlier
    1.15
     Critics
    1.13
     Previously
    1.13
     Though
    1.11
     Initially
    1.06
     However
    1.06
     Since
    1.05
     Although
    1.04
     Additionally
    1.02
     Currently
    1.00
    Activations Density 0.405%

    No Known Activations