© 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. 6-RES-JB
    11. 9568
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical and syntax errors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or procedural issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Machine
    -0.81
    Comb
    -0.79
    Kn
    -0.77
    Tube
    -0.76
    gob
    -0.76
    Chel
    -0.75
    Ken
    -0.74
    Carl
    -0.74
     Helic
    -0.73
    Camp
    -0.73
    POSITIVE LOGITS
     pathology
    0.89
     deprivation
    0.83
     intolerance
    0.81
     significance
    0.81
     status
    0.80
     propensity
    0.80
     extortion
    0.80
     obstruction
    0.79
     affinity
    0.79
     trouble
    0.77
    Activations Density 0.557%

    No Known Activations