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. 7290
    Prev
    Next
    INDEX
    Explanations

    the phrase "Why not" followed by a suggestion or question

    oai_token-act-pair · gpt-3.5-turbo

    phrases suggesting alternative possibilities or proposals

    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
    ixel
    -0.73
    photo
    -0.69
    KI
    -0.62
    orge
    -0.62
    Runner
    -0.62
    BILITIES
    -0.61
    wik
    -0.60
    itivity
    -0.60
    velength
    -0.59
    Ó
    -0.59
    POSITIVE LOGITS
    ?]
    0.88
    itia
    0.75
    ]).
    0.75
    ucc
    0.74
     intervene
    0.70
    ]);
    0.68
     invoke
    0.64
    instead
    0.63
     Seym
    0.62
    ickets
    0.62
    Activations Density 0.030%

    No Known Activations