© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3271
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistics and metrics

    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
    ï¸
    -0.75
    apego
    -0.65
     backdrop
    -0.61
    unity
    -0.61
    urity
    -0.59
     symbol
    -0.59
    arity
    -0.59
     extraord
    -0.59
    orpor
    -0.57
    another
    -0.57
    POSITIVE LOGITS
     respondents
    1.50
     surveyed
    1.26
     households
    1.26
     applicants
    1.15
     subscribers
    1.06
     polled
    1.06
     earners
    1.06
     visitors
    1.03
     attendees
    1.01
     fatalities
    1.01
    Activations Density 0.255%

    No Known Activations