© 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. 11-RES-JB
    11. 19316
    Prev
    Next
    INDEX
    Explanations

    screens or screenshots

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "screen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aternal
    -0.73
    doms
    -0.67
    istani
    -0.65
    ortium
    -0.64
     Scientific
    -0.64
    akeru
    -0.64
    shire
    -0.63
     Dangerous
    -0.60
     plur
    -0.59
    vernment
    -0.59
    POSITIVE LOGITS
    plays
    1.27
    grab
    1.24
    writer
    1.16
    writers
    1.15
    avers
    1.11
    caps
    1.11
    printed
    1.11
    writing
    1.05
    aver
    1.03
    casts
    0.94
    Activations Density 0.036%

    No Known Activations