© 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. 17694
    Prev
    Next
    INDEX
    Explanations

    a mix of different languages or dialects

    oai_token-act-pair · gpt-3.5-turbo

    sections related to names and titles, particularly those with repeated or emphasized letters

    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
     predictable
    -0.76
     warranted
    -0.72
     believable
    -0.72
     financially
    -0.70
     financial
    -0.70
     digitally
    -0.69
     makeup
    -0.68
     budget
    -0.68
     contingency
    -0.68
     discriminatory
    -0.67
    POSITIVE LOGITS
    inav
    1.35
    anus
    1.30
    ija
    1.29
    inka
    1.23
    inia
    1.19
    unda
    1.18
    okia
    1.18
    aceae
    1.18
    olor
    1.17
    idas
    1.17
    Activations Density 0.564%

    No Known Activations