© 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. 0-RES-JB
    11. 22403
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to conflict or competition

    oai_token-act-pair · gpt-3.5-turbo

    the word "between" and contexts related to contrasts or relationships in discussions

    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
     ceiling
    -0.71
     sugar
    -0.63
     Ce
    -0.63
     Football
    -0.62
     guidance
    -0.61
     County
    -0.60
     Resolution
    -0.60
     Prob
    -0.59
     course
    -0.58
     Targ
    -0.58
    POSITIVE LOGITS
    between
    3.44
    ÅĤ
    1.32
    Between
    1.23
    behind
    1.15
    inel
    1.10
    mid
    1.06
    ahead
    1.04
    camera
    1.02
    leon
    0.98
    progress
    0.95
    Activations Density 0.040%

    No Known Activations