© 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. 2635
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "fail" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of failure or unsuccessful attempts

    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
    uci
    -0.72
    éĹĺ
    -0.69
    raph
    -0.64
    uilt
    -0.60
    ï¸ı
    -0.60
     Emblem
    -0.57
     Psychiatric
    -0.57
    mental
    -0.56
    iazep
    -0.56
    oda
    -0.56
    POSITIVE LOGITS
     unsuccessful
    1.64
     success
    1.51
    success
    1.49
    successful
    1.35
     successful
    1.31
     succeeds
    1.30
     succeed
    1.30
     failure
    1.30
     succeeded
    1.29
     successes
    1.29
    Activations Density 0.512%

    No Known Activations