© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 6976
    Prev
    Next
    INDEX
    Explanations

    Apple products starting with the letter 'i'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'i'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.69
    rique
    -0.69
     Darwin
    -0.69
     Down
    -0.69
     Rept
    -0.69
     Territ
    -0.68
    tnc
    -0.66
    perties
    -0.65
     Windsor
    -0.65
     Ryder
    -0.64
    POSITIVE LOGITS
    pec
    1.18
    ota
    1.03
    'm
    1.02
    ulia
    1.00
    ibo
    0.99
    omm
    0.95
    ye
    0.94
    GPU
    0.94
    ordan
    0.93
    wi
    0.92
    Activations Density 0.014%

    No Known Activations