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. 2-RES-JB
    6. 24302
    Prev
    Next
    INDEX
    Explanations

    non-English characters that might be part of a specific language or writing system

    oai_token-act-pair · gpt-3.5-turbo

    non-standard characters or potentially corrupted text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.75
    ebus
    -0.75
    gettable
    -0.73
    raints
    -0.72
    merce
    -0.72
    erald
    -0.67
    hibited
    -0.66
     hemor
    -0.66
    ãĥ£
    -0.66
    goers
    -0.65
    POSITIVE LOGITS
    ½
    1.23
    âĶĢâĶĢ
    0.99
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.92
    ¼
    0.88
    ת
    0.87
    ×ķ
    0.86
    Ģ
    0.80
    ħ
    0.80
    Ĺ
    0.79
    lement
    0.76
    Activations Density 0.006%

    No Known Activations