© 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. 10-RES-JB
    11. 7882
    Prev
    Next
    INDEX
    Explanations

    words related to challenges or obstacles to overcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obstacles and challenges in a context involving effort and perseverance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pire
    -0.58
    aah
    -0.57
     Somebody
    -0.57
     of
    -0.56
     Suppose
    -0.54
     Of
    -0.53
     OF
    -0.52
     Crazy
    -0.52
     fucked
    -0.52
    uberty
    -0.52
    POSITIVE LOGITS
    clusive
    0.69
    forth
    0.65
    xtap
    0.61
    uous
    0.61
     scant
    0.61
    uously
    0.61
     earliest
    0.60
    ouble
    0.59
    ienne
    0.59
    ially
    0.59
    Activations Density 0.612%

    No Known Activations