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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21068
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    conditional clauses and phrases that introduce comparisons or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.69
    ciplinary
    -0.63
    iencies
    -0.62
    ":-
    -0.59
    HOU
    -0.58
     ();
    -0.57
    ":[{"
    -0.57
     {\
    -0.55
     resil
    -0.55
     Cheong
    -0.53
    POSITIVE LOGITS
    ?)
    1.42
    !)
    1.34
    !),
    1.30
    -)
    1.28
    )
    1.26
    ?),
    1.25
    *)
    1.22
    )."
    1.22
    ?).
    1.21
    +)
    1.18
    Activations Density 0.145%

    No Known Activations