© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    phrases related to sporting events

    oai_token-act-pair · gpt-3.5-turbo

    references to participation and decision-making in competitive contexts

    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
     Depression
    -0.76
    Detect
    -0.75
    usterity
    -0.75
     correction
    -0.74
    ©¶æ¥µ
    -0.71
     devastation
    -0.69
     cures
    -0.69
     Disaster
    -0.68
     Repair
    -0.68
     Detect
    -0.68
    POSITIVE LOGITS
     participate
    1.61
     participated
    1.49
     attend
    1.42
     participates
    1.40
     participating
    1.39
     attending
    1.33
    particip
    1.32
     competed
    1.29
     participation
    1.25
     audition
    1.25
    Activations Density 0.530%

    No Known Activations