© 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. 10-RES-JB
    11. 20337
    Prev
    Next
    INDEX
    Explanations

    comparisons between different levels of ability or quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to proficiency and comparisons of skill levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancies
    -0.76
    hea
    -0.71
    risome
    -0.70
    iann
    -0.69
    ategory
    -0.69
    fty
    -0.69
    NetMessage
    -0.65
    ums
    -0.65
    anism
    -0.65
    oya
    -0.65
    POSITIVE LOGITS
     behaved
    1.03
     acquainted
    0.94
     negotiators
    0.93
     buddies
    0.88
     negotiator
    0.87
     suited
    0.87
     performers
    0.83
    friends
    0.83
    enough
    0.81
     defensively
    0.80
    Activations Density 0.113%

    No Known Activations