© 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. 14083
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal development and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal agency and decision-making

    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
    oshenko
    -0.70
     solicitor
    -0.62
    govtrack
    -0.61
    Reilly
    -0.60
     Royale
    -0.59
    tip
    -0.59
    edit
    -0.59
    market
    -0.58
     torpedo
    -0.58
    allo
    -0.58
    POSITIVE LOGITS
     ourselves
    2.20
     our
    1.47
     OUR
    1.18
     selves
    1.16
    Our
    1.10
     unconsciously
    1.08
     Our
    1.00
     we
    0.92
     ours
    0.91
    cients
    0.91
    Activations Density 0.707%

    No Known Activations