© 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. 3031
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to quick actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Quick" or variations thereof

    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
    #$#$
    -0.73
    reon
    -0.72
    ortmund
    -0.71
    åĨ
    -0.69
    ICAN
    -0.69
    ÃįÃį
    -0.67
    ucc
    -0.67
    gypt
    -0.65
    uthor
    -0.65
    gdala
    -0.65
    POSITIVE LOGITS
    ening
    1.18
    ened
    1.17
    itude
    1.05
     succession
    1.05
     turnaround
    1.03
    lime
    1.00
    eners
    1.00
    ness
    0.97
    fix
    0.94
    aneously
    0.93
    Activations Density 0.037%

    No Known Activations