© 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. 12877
    Prev
    Next
    INDEX
    Explanations

    keywords related to attributes or characteristics of something, potentially describing features, characteristics, or qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to various aspects of existence or situations related to acceptance and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    nesses
    -0.57
    rome
    -0.57
     }}
    -0.56
     Dragonbound
    -0.55
     CLSID
    -0.54
    bey
    -0.53
    ¬¼
    -0.52
    avis
    -0.51
    ves
    -0.51
    ROR
    -0.51
    POSITIVE LOGITS
     including
    1.45
     ranging
    1.36
     besides
    1.25
    including
    1.17
     Including
    1.14
     pertaining
    1.06
     includ
    1.03
     namely
    1.01
    ranging
    1.00
     such
    1.00
    Activations Density 0.622%

    No Known Activations