© 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. 8-RES-JB
    11. 20111
    Prev
    Next
    INDEX
    Explanations

    structured phrases starting with "with the" followed by a noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating associations or relationships, particularly focusing on the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.88
    lass
    -0.83
    ares
    -0.83
    tick
    -0.81
    hip
    -0.80
    adobe
    -0.77
    ','
    -0.73
    las
    -0.72
    ItemTracker
    -0.72
    arse
    -0.71
    POSITIVE LOGITS
     exception
    1.60
     exceptions
    1.47
     caveat
    1.39
     emphasis
    1.28
     consequ
    1.26
     implication
    1.23
     attendant
    1.19
     caveats
    1.16
     notable
    1.11
     resultant
    1.10
    Activations Density 0.180%

    No Known Activations