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. 18973
    Prev
    Next
    INDEX
    Explanations

    financial terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    financial and contractual terms and conditions

    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
    Capture
    -0.64
    scape
    -0.62
    nea
    -0.60
    ffen
    -0.59
     VID
    -0.58
    eworld
    -0.56
    plane
    -0.55
    ramid
    -0.55
    issance
    -0.55
    iasis
    -0.54
    POSITIVE LOGITS
     ranging
    1.34
     totaling
    1.31
     gal
    1.26
    pring
    0.97
     tot
    0.93
     similar
    0.92
    poons
    0.92
     resembling
    0.92
     varying
    0.91
     analogous
    0.88
    Activations Density 0.461%

    No Known Activations