© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    strict rules, guidelines, or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "strict" and its variations 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
    ilater
    -0.84
    ovember
    -0.83
    assies
    -0.77
    querade
    -0.74
    xxxxxxxx
    -0.70
    ********
    -0.70
    ocamp
    -0.70
    akeru
    -0.69
    NetMessage
    -0.68
    ̶
    -0.68
    POSITIVE LOGITS
    ures
    1.19
     adherence
    1.17
    ness
    0.96
     strict
    0.89
    nesses
    0.88
    est
    0.88
     adherent
    0.87
     limits
    0.86
     restrictive
    0.85
     scrutiny
    0.84
    Activations Density 0.035%

    No Known Activations