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. 2251
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and software systems

    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
    )].
    -0.52
    !]
    -0.47
    urse
    -0.44
    sbm
    -0.44
    .):
    -0.40
    awaru
    -0.39
    ?]
    -0.39
    Reviewer
    -0.39
    [/
    -0.39
    @@@@@@@@
    -0.37
    POSITIVE LOGITS
    branded
    0.44
     respectively
    0.41
    fitted
    0.40
    derived
    0.38
    picked
    0.38
     aeros
    0.38
    announced
    0.38
    nels
    0.38
     targeting
    0.38
     targeted
    0.37
    Activations Density 3.555%

    No Known Activations