© 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. 16417
    Prev
    Next
    INDEX
    Explanations

    words related to hypothetical scenarios or conditions, particularly starting with "Had"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional scenarios or hypothetical situations

    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
     Today
    -0.61
    ensing
    -0.61
    PI
    -0.60
    Soc
    -0.57
     Duty
    -0.56
    Reward
    -0.54
     Hof
    -0.54
     Jou
    -0.54
     salute
    -0.54
     outp
    -0.54
    POSITIVE LOGITS
    iths
    1.23
    ith
    1.03
    rons
    0.98
    wolves
    0.90
     been
    0.88
    wolf
    0.88
    rien
    0.87
     hoped
    0.85
    been
    0.83
    rian
    0.80
    Activations Density 0.099%

    No Known Activations