© 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. 24331
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    elements of decision-making or choices

    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
    tsy
    -0.60
    stown
    -0.58
    earchers
    -0.58
    mt
    -0.57
    ricular
    -0.56
    abase
    -0.54
    advertisement
    -0.54
    DonaldTrump
    -0.53
    tal
    -0.53
    owsky
    -0.53
    POSITIVE LOGITS
     Both
    2.22
    Both
    2.17
     both
    1.97
     respectively
    1.89
     latter
    1.84
    both
    1.79
     Neither
    1.75
     neither
    1.67
    Neither
    1.66
     whichever
    1.46
    Activations Density 0.938%

    No Known Activations