© 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. 6-RES-JB
    11. 11553
    Prev
    Next
    INDEX
    Explanations

    instances where there's a likelihood or possibility of an event occurring

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the likelihood or probability of an event occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.88
    zeb
    -0.77
    cht
    -0.75
    ilver
    -0.73
    empl
    -0.72
    Materials
    -0.72
    Keys
    -0.71
    ils
    -0.71
    ashion
    -0.69
    artney
    -0.68
    POSITIVE LOGITS
    llor
    0.81
     Rouhani
    0.79
     probability
    0.76
     pron
    0.71
     occurrence
    0.71
     admission
    0.70
     inacc
    0.69
     chance
    0.69
     likelihood
    0.69
    finder
    0.68
    Activations Density 0.055%

    No Known Activations