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. 13060
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a change or transition

    oai_token-act-pair · gpt-3.5-turbo

    instances of past actions or changes over time

    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
     Ney
    -0.66
    ocal
    -0.63
     ideal
    -0.62
     Defenders
    -0.58
     backbone
    -0.57
    iour
    -0.56
     constituents
    -0.56
     withstand
    -0.56
    ribes
    -0.55
    ested
    -0.54
    POSITIVE LOGITS
    isode
    0.77
    Ń·
    0.77
    Cooldown
    0.76
     Bye
    0.71
     adjourn
    0.70
    cember
    0.69
     abruptly
    0.67
    END
    0.67
     trave
    0.66
    ĻĤ
    0.66
    Activations Density 0.301%

    No Known Activations