© 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. 2-RES-JB
    11. 23961
    Prev
    Next
    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Garen."

    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
     srfAttach
    -0.76
     Accuracy
    -0.69
     Labrador
    -0.64
     extent
    -0.64
    VALUE
    -0.63
    urious
    -0.60
     jerk
    -0.60
     degree
    -0.59
    aternity
    -0.58
     Yard
    -0.57
    POSITIVE LOGITS
    wen
    0.84
    ko
    0.82
    jen
    0.82
    kie
    0.82
    swer
    0.82
    nes
    0.82
    thia
    0.81
    stant
    0.81
    ses
    0.81
    lied
    0.81
    Activations Density 0.004%

    No Known Activations