© 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. 4-RES-JB
    11. 14789
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to galleries or collections of artwork

    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
    jab
    -0.82
    nir
    -0.72
    ially
    -0.70
     nib
    -0.68
    ties
    -0.66
    ministic
    -0.65
    zee
    -0.64
    theless
    -0.63
    teenth
    -0.61
    terday
    -0.61
    POSITIVE LOGITS
     Thumbnails
    1.30
     Gallery
    1.11
    Gallery
    1.06
    gallery
    0.88
     galleries
    0.84
    Images
    0.83
     gallery
    0.82
    OTOS
    0.82
    Prev
    0.81
     exhibitions
    0.80
    Activations Density 0.008%

    No Known Activations