© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11173
    Prev
    Next
    INDEX
    Explanations

    information related to governmental departments and agencies

    oai_token-act-pair · gpt-3.5-turbo

    instances of clauses, particularly those that include commas suggesting additional information or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosa
    -0.63
     transformations
    -0.63
     arcs
    -0.62
     sins
    -0.62
     imaginable
    -0.62
    iq
    -0.61
     havoc
    -0.60
     contagious
    -0.59
     attractiveness
    -0.59
    jad
    -0.59
    POSITIVE LOGITS
     headquartered
    0.87
     namely
    0.83
     chaired
    0.82
     Colleges
    0.80
     staffed
    0.79
     including
    0.79
     culminating
    0.77
     judiciary
    0.77
     consulted
    0.76
    sonian
    0.76
    Activations Density 0.387%

    No Known Activations