© 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. 9-RES-JB
    11. 477
    Prev
    Next
    INDEX
    Explanations

    terms related to interaction or balance between different elements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to interactions, relationships, and balance between different elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    den
    -0.64
     Citation
    -0.64
     Sabha
    -0.63
    deen
    -0.62
    DER
    -0.60
     Regist
    -0.60
    uled
    -0.59
    ever
    -0.59
    dule
    -0.58
     Others
    -0.57
    POSITIVE LOGITS
     between
    1.60
    between
    1.33
     Between
    1.31
    otomy
    1.12
     BET
    1.09
    Between
    0.88
    ativity
    0.88
     separating
    0.84
    yll
    0.79
     matrix
    0.78
    Activations Density 0.200%

    No Known Activations