© 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. 2437
    Prev
    Next
    INDEX
    Explanations

    personal reflections or comparisons with emphasis on change, perspective, and imagination

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comparison and emphasis on personal experiences

    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
    alore
    -0.59
    raltar
    -0.58
    istries
    -0.57
    urst
    -0.56
     Firm
    -0.55
     Christy
    -0.54
    leted
    -0.54
    skirts
    -0.53
    onen
    -0.52
     Tier
    -0.52
    POSITIVE LOGITS
     barg
    1.11
     ever
    1.08
     realize
    0.89
    ":[
    0.87
     realizes
    0.85
     imagin
    0.83
     imagined
    0.83
     realise
    0.82
    ever
    0.82
     EVER
    0.81
    Activations Density 0.147%

    No Known Activations