© 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. 9-RES-JB
    11. 2546
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and blame

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atl
    -0.77
    ixon
    -0.77
    soever
    -0.71
    Mine
    -0.70
    wang
    -0.69
    edin
    -0.69
    illin
    -0.68
    ogens
    -0.67
    OTAL
    -0.66
    iple
    -0.65
    POSITIVE LOGITS
     failing
    1.24
     daring
    1.16
     refusing
    1.15
     abandoning
    1.14
     having
    1.11
     being
    1.09
     believing
    1.07
     allowing
    1.05
     rejecting
    1.03
     ruining
    1.03
    Activations Density 0.105%

    No Known Activations