© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14980
    Prev
    Next
    INDEX
    Explanations

    phrases related to shifts in power dynamics or status quo

    oai_token-act-pair · gpt-3.5-turbo

    metaphors and phrases related to change and transition

    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
    ths
    -0.74
    Eva
    -0.66
    edly
    -0.59
     proficiency
    -0.56
    OURCE
    -0.55
    bil
    -0.55
    places
    -0.54
    tein
    -0.54
     impressions
    -0.54
     criminally
    -0.53
    POSITIVE LOGITS
     goes
    0.75
     ain
    0.73
     flowed
    0.72
     explodes
    0.71
     went
    0.71
     belongs
    0.68
     belonged
    0.68
     clicked
    0.68
     swung
    0.66
     peaked
    0.66
    Activations Density 0.298%

    No Known Activations