© 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. 12142
    Prev
    Next
    INDEX
    Explanations

    instances where the word "counting" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of counting

    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
    ensable
    -0.70
     Correspond
    -0.67
    ifest
    -0.66
     Eden
    -0.65
    agar
    -0.64
    ggie
    -0.62
    por
    -0.62
    ieties
    -0.61
    asus
    -0.61
    etheus
    -0.61
    POSITIVE LOGITS
    enance
    1.42
    ENCY
    0.86
    downs
    0.78
    stakes
    0.74
     counting
    0.74
    esses
    0.71
     bells
    0.71
    reys
    0.69
    encies
    0.69
     counted
    0.67
    Activations Density 0.011%

    No Known Activations