© 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. 11-RES-JB
    11. 7043
    Prev
    Next
    INDEX
    Explanations

    phrases related to skill levels or expertise levels in various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to catering to both beginners and experienced individuals in a specific hobby or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.75
    vote
    -0.68
     è£ıç
    -0.67
    forcing
    -0.66
    inez
    -0.65
    facts
    -0.65
    Wars
    -0.65
    esar
    -0.64
    anism
    -0.63
    Correct
    -0.62
    POSITIVE LOGITS
     beginners
    1.62
     novice
    1.46
     beginner
    1.43
     seasoned
    1.37
     newcomers
    1.36
     enthusiasts
    1.25
     professionals
    1.24
     hobby
    1.24
     casual
    1.18
     inexperienced
    1.15
    Activations Density 0.298%

    No Known Activations