© 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. 22469
    Prev
    Next
    INDEX
    Explanations

    phrases related to jumping on board or expressing a strong opinion on a topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "jumping on."

    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
     hallmark
    -0.67
    heastern
    -0.64
    Policy
    -0.64
    minus
    -0.63
    lf
    -0.62
     unchanged
    -0.61
    resa
    -0.61
    don
    -0.61
     absent
    -0.61
    pdf
    -0.60
    POSITIVE LOGITS
     bandwagon
    1.03
     conclusions
    0.90
     hoops
    0.80
     leaps
    0.79
    obin
    0.77
    ioxide
    0.75
     Adren
    0.68
    aughs
    0.66
     hoop
    0.65
    ubes
    0.64
    Activations Density 0.127%

    No Known Activations