© 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. 3627
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical code or programming elements

    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
    atform
    -0.91
    esis
    -0.75
     Ago
    -0.70
    ulhu
    -0.69
     Carbuncle
    -0.69
    kinson
    -0.68
    lehem
    -0.68
    atcher
    -0.67
    romeda
    -0.66
    agna
    -0.66
    POSITIVE LOGITS
    taboola
    1.04
    pret
    1.01
    dict
    0.93
    bably
    0.92
    blank
    0.91
    chance
    0.86
    default
    0.83
    self
    0.83
    tra
    0.81
    dep
    0.81
    Activations Density 0.009%

    No Known Activations