© 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. 8-RES-JB
    11. 23652
    Prev
    Next
    INDEX
    Explanations

    references to competitions or challenges

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "contest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahon
    -0.72
    âĹ¼
    -0.71
    haar
    -0.68
    Else
    -0.64
     Metallic
    -0.63
     Leaf
    -0.63
    ijk
    -0.61
    ths
    -0.61
    minent
    -0.61
    cano
    -0.59
    POSITIVE LOGITS
    eering
    1.05
    eers
    0.97
    ants
    0.89
    naire
    0.88
    ing
    0.87
    hips
    0.86
     winners
    0.82
    arium
    0.78
    eer
    0.77
    ors
    0.76
    Activations Density 0.029%

    No Known Activations