© 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. 8-RES-JB
    11. 6788
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "if only" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express conditionality or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contention
    -0.64
    abis
    -0.61
    elist
    -0.58
    ffen
    -0.55
    Ö¼
    -0.55
    ibel
    -0.54
    alez
    -0.54
    ibal
    -0.54
     Ahmad
    -0.53
     UNHCR
    -0.52
    POSITIVE LOGITS
     temporarily
    0.72
    hai
    0.69
     momentarily
    0.69
     marginally
    0.69
    hap
    0.68
    amaz
    0.67
    tem
    0.64
     cared
    0.62
    imes
    0.62
    icable
    0.62
    Activations Density 0.077%

    No Known Activations