© 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 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. 4-RES-JB
    11. 4847
    Prev
    Next
    INDEX
    Explanations

    words related to a change in direction or action

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement or change of direction

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

    No Comments

    Negative Logits
     Mb
    -0.74
     Administrator
    -0.61
     succ
    -0.59
    Cu
    -0.59
     awaits
    -0.59
     liable
    -0.56
     Zac
    -0.56
    ian
    -0.54
     Helpful
    -0.54
     harmed
    -0.54
    POSITIVE LOGITS
     tempo
    0.81
    shape
    0.78
    grading
    0.75
    ivot
    0.73
    ilight
    0.72
    upt
    0.72
    raviolet
    0.71
    akedown
    0.70
    otomy
    0.70
    ortun
    0.69
    Activations Density 0.125%

    No Known Activations