© 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. 9-RES-JB
    11. 18142
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the quality or characteristics of something

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to evaluations of authenticity or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GROUP
    -0.76
    @#&
    -0.73
     Guys
    -0.69
    inton
    -0.69
    ievers
    -0.68
    amiya
    -0.66
    Newsletter
    -0.66
    rians
    -0.66
     coli
    -0.65
     oneself
    -0.65
    POSITIVE LOGITS
     namesake
    1.34
     counterpart
    1.33
     counterparts
    1.25
     existence
    1.13
     predecessor
    1.13
     cousin
    1.12
     origins
    1.11
     nature
    1.07
     predecessors
    1.07
     sibling
    1.06
    Activations Density 0.316%

    No Known Activations