© 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. 18410
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or theme "endorf"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "endorse" and its variations in the context of discussions involving acknowledgment or approval

    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
     Immunity
    -0.62
    keyes
    -0.62
     methodological
    -0.60
     Primordial
    -0.59
     Dating
    -0.59
    Cath
    -0.58
     occupancy
    -0.58
    Catholic
    -0.58
     Tant
    -0.56
    Bed
    -0.56
    POSITIVE LOGITS
    endor
    1.41
    ffer
    0.90
    abilia
    0.90
    ibel
    0.78
    cade
    0.78
    ption
    0.77
    ODY
    0.77
    ff
    0.77
    enance
    0.75
    DAQ
    0.75
    Activations Density 0.005%

    No Known Activations