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

    Neuronpedia

    APICircuit 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. 18213
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities associated with the document's content

    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
     Haram
    -0.75
    âĶĢâĶĢ
    -0.73
     underwater
    -0.64
     Teddy
    -0.61
     Border
    -0.60
     respecting
    -0.59
     Dangerous
    -0.59
    ··
    -0.58
     tribal
    -0.58
     OPS
    -0.58
    POSITIVE LOGITS
    elman
    1.23
    mons
    1.21
    mel
    1.18
    opoulos
    1.16
    ansky
    1.14
    pson
    1.14
    anski
    1.13
    inski
    1.13
    ayne
    1.11
    monds
    1.08
    Activations Density 0.099%

    No Known Activations