© 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. 17172
    Prev
    Next
    INDEX
    Explanations

    proper nouns used as names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Mir" 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
    ential
    -0.66
     LCS
    -0.63
    YC
    -0.63
     Combine
    -0.63
    ãĤī
    -0.61
    CAST
    -0.60
     Primordial
    -0.60
     Prompt
    -0.58
    enegger
    -0.58
    ggies
    -0.57
    POSITIVE LOGITS
    rors
    1.40
    acles
    1.35
    rored
    1.33
    acle
    1.17
    ror
    1.08
    abella
    1.03
    abilia
    1.03
    iam
    0.93
    ial
    0.91
    abel
    0.90
    Activations Density 0.027%

    No Known Activations