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. 21295
    Prev
    Next
    INDEX
    Explanations

    objects being described in detail

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe items accompanied by the word "with."

    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
    thren
    -0.74
    ights
    -0.70
    hack
    -0.70
    borgh
    -0.67
    ati
    -0.66
    Asia
    -0.63
    cemic
    -0.63
    Leaks
    -0.63
    phrine
    -0.63
    iance
    -0.63
    POSITIVE LOGITS
    stood
    1.53
     regard
    1.38
     regards
    1.31
    drawn
    1.17
     respect
    1.14
    standing
    1.06
     impunity
    1.05
    draw
    1.05
    holding
    0.87
     whom
    0.78
    Activations Density 0.174%

    No Known Activations