© 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. 14128
    Prev
    Next
    INDEX
    Explanations

    discussion regarding local contractors working on energy upgrades for a program

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to social issues or community challenges

    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
     Nobel
    -0.86
     synthesis
    -0.77
     Ago
    -0.73
    rosso
    -0.73
     synthes
    -0.72
    izons
    -0.71
     Analyst
    -0.71
     Luxem
    -0.70
     Journals
    -0.69
    alyst
    -0.69
    POSITIVE LOGITS
     nuisance
    1.40
     inconven
    1.39
     unsafe
    1.39
     inconvenience
    1.38
     tresp
    1.25
     disrespectful
    1.22
     trespass
    1.19
     hassle
    1.18
     disturbance
    1.10
     vandalism
    1.09
    Activations Density 0.747%

    No Known Activations