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. 7-RES-JB
    6. 20112
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences and subsequent actions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to consequences and outcomes of actions

    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
     Registered
    -0.67
     Cosponsors
    -0.65
    enhagen
    -0.64
    anmar
    -0.61
    ãĤ¶
    -0.60
    ATS
    -0.60
     Browse
    -0.60
    é¾į
    -0.60
     Library
    -0.58
     Mountain
    -0.58
    POSITIVE LOGITS
     irreversible
    0.92
     outweigh
    0.90
     unforeseen
    0.81
     outwe
    0.78
    .''.
    0.77
     predetermined
    0.75
     payoff
    0.73
     catast
    0.72
    ?".
    0.72
    .</
    0.71
    Activations Density 1.476%

    No Known Activations