© 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. 6-RES-JB
    11. 3608
    Prev
    Next
    INDEX
    Explanations

    keywords related to image captions, specifically where the word "Photos" is included

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Photos."

    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
    ministic
    -0.84
    phas
    -0.82
    osc
    -0.73
    oshenko
    -0.71
    merce
    -0.69
    rance
    -0.67
    stood
    -0.67
    inence
    -0.67
    _-
    -0.67
     speech
    -0.65
    POSITIVE LOGITS
    ynthesis
    0.98
     Photos
    0.94
    Gallery
    0.90
    Photos
    0.87
    ensitive
    0.81
     Caption
    0.80
     Thumbnails
    0.79
    OTOS
    0.78
     captcha
    0.76
    ards
    0.72
    Activations Density 0.010%

    No Known Activations