© 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. 1-RES-JB
    11. 16439
    Prev
    Next
    INDEX
    Explanations

    photographs or images with varying emphasis on the importance and quality

    oai_token-act-pair · gpt-3.5-turbo

    references to photos and photographic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irth
    -0.82
    estern
    -0.78
    otom
    -0.74
    auri
    -0.72
    rane
    -0.72
    inav
    -0.71
    pperc
    -0.71
     fielding
    -0.70
    ministic
    -0.70
    ells
    -0.69
    POSITIVE LOGITS
    photo
    1.39
    >>>>>>>>
    1.15
    photos
    0.97
     Thumbnails
    0.96
     PHOTO
    0.95
     IMAGES
    0.87
    journal
    0.84
    Photos
    0.81
     td
    0.81
    Photo
    0.80
    Activations Density 0.003%

    No Known Activations