© 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. 10-RES-JB
    11. 12834
    Prev
    Next
    INDEX
    Explanations

    questions or statements about general knowledge or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to conveying information or experiences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swer
    -0.73
    estone
    -0.70
    idon
    -0.67
    raid
    -0.67
    robe
    -0.66
    odge
    -0.66
    xon
    -0.64
    scan
    -0.64
    ivery
    -0.64
    etts
    -0.63
    POSITIVE LOGITS
     happens
    1.48
     constitutes
    1.42
     happened
    1.25
     transpired
    1.17
     separates
    1.17
     distinguishes
    1.14
     motiv
    1.10
     kinds
    1.09
     qualifies
    1.07
     makes
    1.05
    Activations Density 0.095%

    No Known Activations