© 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. 23393
    Prev
    Next
    INDEX
    Explanations

    words related to technological terms, like domains, coding, and software

    oai_token-act-pair · gpt-3.5-turbo

    content related to online services and technology

    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
     Stern
    -0.73
     Calder
    -0.68
     McH
    -0.68
     lifelong
    -0.68
     grounding
    -0.68
     Nanto
    -0.68
     sentencing
    -0.64
     sprawling
    -0.64
     breadth
    -0.64
     Roe
    -0.63
    POSITIVE LOGITS
    @
    1.32
    blogspot
    1.13
    Plugin
    1.12
    Blog
    1.11
    ById
    1.07
    âĦ¢
    1.07
    _-_
    1.06
    Website
    1.06
    ()
    1.03
    Club
    1.02
    Activations Density 0.253%

    No Known Activations