© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6693
    Prev
    Next
    INDEX
    Explanations

    technical specifications or product details

    oai_token-act-pair · gpt-3.5-turbo

    product specifications and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     respectively
    -0.71
     downstream
    -0.59
    )."
    -0.59
    .""
    -0.58
     unaff
    -0.55
    ]."
    -0.54
     mere
    -0.53
    .).
    -0.53
     thereof
    -0.53
     upstream
    -0.52
    POSITIVE LOGITS
     Edit
    1.08
    !:
    1.05
     âĵĺ
    1.02
     Profile
    1.00
     :
    0.96
    %:
    0.94
    :
    0.92
    ':
    0.91
     Releases
    0.81
    ¶
    0.81
    Activations Density 0.951%

    No Known Activations