© 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. 0-RES-JB
    11. 4114
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Todd."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Todd."

    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
     revolutions
    -0.68
     corpus
    -0.65
     Dynamo
    -0.65
    celona
    -0.64
     cubes
    -0.63
    Ĵ
    -0.63
     summons
    -0.62
     summoning
    -0.62
     UR
    -0.62
    apor
    -0.61
    POSITIVE LOGITS
     Todd
    3.68
    Todd
    3.58
     todd
    1.65
     Doug
    1.24
     toddlers
    1.21
     Lindsey
    1.18
     Tammy
    1.17
     Jared
    1.10
     Jeffrey
    1.09
     Haley
    1.09
    Activations Density 0.016%

    No Known Activations