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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 8000
    Prev
    Next
    INDEX
    Explanations

    Twitter handles to follow

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Follow" indicating social media references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.84
    inese
    -0.73
     ILCS
    -0.71
    negie
    -0.67
    pressed
    -0.66
    cit
    -0.66
    unicip
    -0.66
    rouse
    -0.65
    ately
    -0.64
    dfx
    -0.64
    POSITIVE LOGITS
     Follow
    0.92
    cies
    0.84
    ers
    0.82
    ership
    0.81
    Follow
    0.78
     @
    0.77
     Updates
    0.75
    ed
    0.72
    follow
    0.69
    ï¸ı
    0.69
    Activations Density 0.020%

    No Known Activations