© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    indications or suggestions in a text

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements related to actions or conditions

    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
     Beg
    -0.67
     incorpor
    -0.61
     territ
    -0.57
     mater
    -0.55
     Discuss
    -0.54
     princ
    -0.54
     Flex
    -0.54
     Thick
    -0.53
     tempo
    -0.53
     enforcing
    -0.52
    POSITIVE LOGITS
     nevertheless
    1.22
     nonetheless
    1.14
     likewise
    1.03
     also
    0.92
     actually
    0.92
     suddenly
    0.92
    also
    0.91
     indeed
    0.87
     invariably
    0.87
     thereby
    0.85
    Activations Density 0.267%

    No Known Activations