© 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. 8-RES-JB
    11. 934
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts or efforts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "attempt" or its variations related to efforts or tries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eyes
    -0.65
    houses
    -0.64
    today
    -0.61
     Carnival
    -0.61
     Tid
    -0.61
     Wrap
    -0.60
     cows
    -0.60
    Edge
    -0.59
     References
    -0.59
    ifa
    -0.58
    POSITIVE LOGITS
    Attempts
    1.02
     unsuccessfully
    0.95
    bles
    0.80
     attempt
    0.79
    URE
    0.78
    URES
    0.75
     attempts
    0.75
    ossible
    0.73
    orneys
    0.71
    ossibility
    0.70
    Activations Density 0.047%

    No Known Activations