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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6081
    Prev
    Next
    INDEX
    Explanations

    decimal numbers expressed in a specific format (number, number, number)

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to measurements or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CAM
    -0.70
     Ember
    -0.66
     Soldiers
    -0.66
     ever
    -0.65
     cottage
    -0.64
     worsh
    -0.64
     gest
    -0.64
     portrait
    -0.64
     Alexandra
    -0.64
     CES
    -0.63
    POSITIVE LOGITS
    5
    1.16
    25
    1.12
    35
    1.11
    8
    1.10
    16
    1.09
    45
    1.09
    05
    1.09
    15
    1.09
    56
    1.08
    30
    1.08
    Activations Density 0.073%

    No Known Activations