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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 2511
    Prev
    Next
    INDEX
    Explanations

    technical and numerical information

    oai_token-act-pair · gpt-3.5-turbo
    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
     eleph
    -0.99
    Þ
    -0.94
     pione
    -0.88
     exting
    -0.86
    aditional
    -0.81
    ò
    -0.79
    ß
    -0.79
    ñ
    -0.79
     enthusi
    -0.78
    anwhile
    -0.77
    POSITIVE LOGITS
    inx
    0.54
    't
    0.50
    igg
    0.49
    ette
    0.48
    athan
    0.48
    itely
    0.46
    --+
    0.46
    vals
    0.46
    ename
    0.45
    val
    0.45
    Activations Density 0.662%

    No Known Activations