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. 4307
    Prev
    Next
    INDEX
    Explanations

    animal-related words and locations, particularly zoos

    oai_token-act-pair · gpt-3.5-turbo

    mention of the word "Zoo" in various 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
    pring
    -0.81
    Interstitial
    -0.79
    acies
    -0.74
    aneous
    -0.74
    idate
    -0.72
    ÑĮ
    -0.71
    itimate
    -0.70
    iating
    -0.70
    owship
    -0.69
    rity
    -0.69
    POSITIVE LOGITS
     Zoo
    0.92
     Tycoon
    0.87
    onga
    0.87
    biology
    0.83
    opia
    0.82
    elling
    0.82
    ÅĤ
    0.81
    ey
    0.80
    zilla
    0.80
     zoo
    0.79
    Activations Density 0.017%

    No Known Activations