© 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. 18844
    Prev
    Next
    INDEX
    Explanations

    instances where the number "one" is mentioned in the context of pairwise comparisons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one" in various contexts

    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
    acements
    -0.80
    uits
    -0.76
    iculty
    -0.75
    inas
    -0.72
    uit
    -0.71
    lov
    -0.71
    ocent
    -0.70
    renches
    -0.70
    models
    -0.70
    unctions
    -0.69
    POSITIVE LOGITS
     apiece
    0.90
     thing
    0.72
    ERA
    0.70
     semester
    0.70
     occupant
    0.69
     accuser
    0.68
     side
    0.68
     hundred
    0.67
     iteration
    0.65
     sided
    0.64
    Activations Density 0.095%

    No Known Activations