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. 9063
    Prev
    Next
    INDEX
    Explanations

    instances where a statement is followed by a conditional "if" clause expressing improvement or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases starting with "if."

    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
    FTWARE
    -0.84
    STAR
    -0.73
    isible
    -0.69
    advertisement
    -0.68
    holm
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    ãĥŃ
    -0.66
    oscopic
    -0.65
    akia
    -0.65
    enos
    -0.64
    POSITIVE LOGITS
    fy
    0.93
    yip
    0.87
    rame
    0.70
     untreated
    0.69
    soever
    0.68
     unchecked
    0.68
     landlords
    0.66
    terday
    0.65
    rets
    0.65
     Kerr
    0.64
    Activations Density 0.058%

    No Known Activations