© 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. 9-RES-JB
    11. 1700
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a decision or a dilemma between two options

    oai_token-act-pair · gpt-3.5-turbo

    phrases that present choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ires
    -0.72
    DERR
    -0.68
    estamp
    -0.63
    bourg
    -0.61
    ENE
    -0.60
    eval
    -0.57
    esson
    -0.57
    istar
    -0.56
    LR
    -0.55
    Nev
    -0.55
    POSITIVE LOGITS
    acle
    1.33
    acles
    1.30
    ifice
    1.28
    Else
    1.27
    chard
    1.24
    acular
    1.20
    nam
    1.19
    chid
    1.12
    nery
    1.12
    lando
    1.11
    Activations Density 0.115%

    No Known Activations