© 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. 2-RES-JB
    11. 23553
    Prev
    Next
    INDEX
    Explanations

    sequences related to montages

    oai_token-act-pair · gpt-3.5-turbo

    references to 'montage' or related concepts in media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stocking
    -0.78
     mole
    -0.70
     inverse
    -0.69
    dfx
    -0.66
     wrench
    -0.66
    WER
    -0.65
    udeb
    -0.65
     srf
    -0.65
    dyl
    -0.65
     damned
    -0.63
    POSITIVE LOGITS
    ments
    1.05
    age
    0.98
    ous
    0.80
    ment
    0.77
    ages
    0.77
    backs
    0.72
    mentation
    0.72
    ously
    0.71
    roups
    0.71
    erity
    0.71
    Activations Density 0.021%

    No Known Activations