© 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. 7-RES-JB
    11. 23965
    Prev
    Next
    INDEX
    Explanations

    social media account usernames

    oai_token-act-pair · gpt-3.5-turbo

    references to social media and communication platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Levant
    -0.68
     carbohyd
    -0.65
     beginners
    -0.64
    lication
    -0.63
    testers
    -0.62
     livest
    -0.62
    etheless
    -0.61
     lengths
    -0.60
     testament
    -0.60
     distances
    -0.59
    POSITIVE LOGITS
    bh
    0.89
    qq
    0.85
    Uk
    0.79
    HQ
    0.77
    zx
    0.77
    uez
    0.77
    jj
    0.76
    xus
    0.75
    qv
    0.74
    OY
    0.73
    Activations Density 0.062%

    No Known Activations