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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3021
    Prev
    Next
    INDEX
    Explanations

    references to different types of birds

    oai_token-act-pair · gpt-3.5-turbo

    references to birds and avian species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaz
    -0.79
    orie
    -0.74
    abase
    -0.71
     Valve
    -0.68
    ilde
    -0.67
     Mori
    -0.67
    Val
    -0.67
     Disp
    -0.65
     moderator
    -0.65
    rik
    -0.64
    POSITIVE LOGITS
     birds
    3.45
    birds
    2.42
     pige
    2.37
     Birds
    2.35
     bird
    2.33
     chickens
    2.25
     ducks
    1.98
     animals
    1.92
    irds
    1.90
     chicks
    1.89
    Activations Density 0.013%

    No Known Activations