© 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. 11-RES-JB
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    superlatives or extreme comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palace
    -0.63
    asar
    -0.61
    instead
    -0.61
     Recording
    -0.59
    utions
    -0.58
    kus
    -0.56
    clusive
    -0.56
     NCT
    -0.56
     Chips
    -0.55
    rompt
    -0.54
    POSITIVE LOGITS
     likely
    1.19
     definitely
    1.17
     certainly
    1.14
     importantly
    1.09
     prominently
    1.07
    likely
    1.03
     notably
    1.00
     commonly
    0.97
     assured
    0.97
     Likely
    0.93
    Activations Density 0.044%

    No Known Activations