© 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. 20444
    Prev
    Next
    INDEX
    Explanations

    dates or time-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to initial reactions or assessments

    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
    Franc
    -0.67
    romeda
    -0.67
    Sav
    -0.67
    md
    -0.66
    knife
    -0.66
    rea
    -0.66
    ren
    -0.65
    Ancient
    -0.64
    Union
    -0.64
    yers
    -0.63
    POSITIVE LOGITS
     stages
    1.03
     impressions
    1.03
    izers
    0.99
    isers
    0.96
    izations
    0.96
     foray
    0.92
     indications
    0.91
    isation
    0.88
    isations
    0.88
     impression
    0.87
    Activations Density 0.047%

    No Known Activations