© 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. 4-RES-JB
    11. 4871
    Prev
    Next
    INDEX
    Explanations

    text related to images or captions within articles

    oai_token-act-pair · gpt-3.5-turbo

    image-related references

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

    No Comments

    Negative Logits
    chance
    -0.70
    secut
    -0.68
    heit
    -0.68
    nesday
    -0.63
     unsuccessfully
    -0.61
    bury
    -0.60
    bush
    -0.60
     etiquette
    -0.60
    entimes
    -0.60
    Attempt
    -0.59
    POSITIVE LOGITS
    otos
    0.84
     guiActiveUnfocused
    0.76
    drm
    0.75
     likeness
    0.73
    itars
    0.70
     Pix
    0.69
    png
    0.69
    ï¸ı
    0.69
    uria
    0.68
    ËĪ
    0.67
    Activations Density 0.408%

    No Known Activations