Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22859
    Prev
    Next
    INDEX
    Explanations

    technical terms related to specifications and details, particularly involving different regions

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to comparisons between entities or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "))
    -0.66
    pires
    -0.57
    )))
    -0.55
    ousands
    -0.54
    efe
    -0.53
    åĩ
    -0.53
    anooga
    -0.53
    Ħ¢
    -0.52
     ))
    -0.51
    alez
    -0.50
    POSITIVE LOGITS
     though
    1.56
     however
    1.41
     tho
    1.21
     but
    0.98
    ;
    0.98
     although
    0.96
     thanks
    0.86
     because
    0.84
    though
    0.83
     meanwhile
    0.81
    Activations Density 1.206%

    No Known Activations