© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17841
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific character or entity, likely named "Yakupov"

    oai_token-act-pair · gpt-3.5-turbo

    names of locations and characters from the context of a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.84
    ancial
    -0.73
    body
    -0.73
     Toast
    -0.69
    yre
    -0.69
    parts
    -0.68
    weights
    -0.68
     ILCS
    -0.68
    builders
    -0.65
     dividend
    -0.65
    POSITIVE LOGITS
     Jak
    1.26
    axter
    0.84
    obs
    0.82
     Bauer
    0.82
    obin
    0.81
    owitz
    0.80
    owski
    0.77
    ansen
    0.75
    onis
    0.73
    kens
    0.73
    Activations Density 0.006%

    No Known Activations