© 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. 6724
    Prev
    Next
    INDEX
    Explanations

    years or dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to studies, reports, and statistics from various years

    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
    osponsors
    -0.93
    ernels
    -0.91
    artifacts
    -0.87
     idols
    -0.85
    Tags
    -0.84
    ittens
    -0.82
    devices
    -0.80
    ifles
    -0.78
    pees
    -0.77
    casts
    -0.77
    POSITIVE LOGITS
     article
    1.33
     study
    1.26
     report
    1.24
     interview
    1.22
     survey
    1.13
     memo
    1.11
     questionnaire
    1.10
     excerpt
    1.08
     statement
    1.06
     Newsweek
    1.02
    Activations Density 0.080%

    No Known Activations