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

    Neuronpedia

    APICircuit 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. 4229
    Prev
    Next
    INDEX
    Explanations

    terms related to natural phenomena or resources

    oai_token-act-pair · gpt-3.5-turbo

    references to natural resources and their implications

    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
    enance
    -0.80
    rav
    -0.70
    ammy
    -0.69
    Reloaded
    -0.69
    eters
    -0.68
     Parables
    -0.65
    lished
    -0.65
    upon
    -0.63
    rez
    -0.63
    bler
    -0.63
    POSITIVE LOGITS
    istic
    1.21
    ization
    1.16
    izations
    1.15
    ized
    1.11
    istically
    1.08
    isation
    1.04
    izes
    1.02
    izable
    0.98
    izing
    0.97
    ised
    0.91
    Activations Density 0.028%

    No Known Activations