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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 22845
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of giving up or discontinuing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "abandon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.69
     Ibid
    -0.68
    acca
    -0.64
    aver
    -0.64
    ammy
    -0.63
    Rh
    -0.63
    APH
    -0.62
    appa
    -0.61
    inn
    -0.60
    above
    -0.59
    POSITIVE LOGITS
     abandon
    1.15
     abandonment
    1.03
     abandoning
    0.82
    fulness
    0.82
     unres
    0.75
    ments
    0.75
     Abandon
    0.73
    plin
    0.72
     disbelief
    0.71
     ditch
    0.70
    Activations Density 0.012%

    No Known Activations