Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11020
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or decisions reached by a group

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "consensus" and its variations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asers
    -0.68
     Tales
    -0.66
    iHUD
    -0.66
    aunts
    -0.64
    taining
    -0.63
    !.
    -0.62
     Presents
    -0.62
    §
    -0.61
    Save
    -0.61
    je
    -0.60
    POSITIVE LOGITS
     consensus
    3.92
     unanim
    2.07
    ensus
    1.78
     unanimous
    1.70
     orthodoxy
    1.31
     equilibrium
    1.19
     majority
    1.18
     agreement
    1.17
     convergence
    1.15
     disagreement
    1.12
    Activations Density 0.020%

    No Known Activations