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. 11-RES-JB
    6. 20223
    Prev
    Next
    INDEX
    Explanations

    phrases related to essential components or elements in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to essential components or elements in various contexts

    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
    iannopoulos
    -0.61
    NOR
    -0.59
    xious
    -0.58
     limbo
    -0.57
    ope
    -0.55
    ebin
    -0.53
    asty
    -0.53
    romeda
    -0.53
    whel
    -0.53
    rahim
    -0.51
    POSITIVE LOGITS
     of
    1.04
     underpin
    0.86
     distinguishing
    0.81
     thereof
    0.74
     determining
    0.73
    ģĸ
    0.70
     motivating
    0.69
     separating
    0.69
     linking
    0.68
     integral
    0.67
    Activations Density 0.176%

    No Known Activations