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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17919
    Prev
    Next
    INDEX
    Explanations

    names of individuals or groups, potentially related to movie credits

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities associated with a variety of roles and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hindsight
    -0.57
     parity
    -0.54
    ogether
    -0.54
     referen
    -0.53
     equival
    -0.52
    ãĥ¼ãĥĨ
    -0.51
     suffice
    -0.51
     necessities
    -0.50
     envy
    -0.50
     corrid
    -0.49
    POSITIVE LOGITS
    ojure
    0.56
    SourceFile
    0.55
     Himself
    0.55
     Senior
    0.53
     Managing
    0.52
     Architects
    0.52
    ken
    0.52
     Jr
    0.51
     Parish
    0.51
     Sr
    0.50
    Activations Density 1.912%

    No Known Activations