Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 4365
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant events, arrests, and consequences in societal contexts

    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
    !.
    -0.69
    inis
    -0.65
    }.
    -0.64
    +.
    -0.60
    };
    -0.59
    cellaneous
    -0.57
    utterstock
    -0.57
    ''.
    -0.56
    .$
    -0.56
    .''
    -0.55
    POSITIVE LOGITS
     lacks
    0.70
     hadn
    0.70
     lacked
    0.69
     should
    0.69
     shouldn
    0.66
     cannot
    0.65
     had
    0.64
     hasn
    0.60
     behaved
    0.60
     exists
    0.58
    Activations Density 0.993%

    No Known Activations