© 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. 6-RES-JB
    11. 3526
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to directional movement

    oai_token-act-pair · gpt-3.5-turbo

    directional words related to movement or place

    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
    gdala
    -0.86
    rast
    -0.78
    anan
    -0.78
    acea
    -0.75
    ocular
    -0.75
    mingham
    -0.74
    INS
    -0.73
    colo
    -0.71
    azo
    -0.71
    tein
    -0.69
    POSITIVE LOGITS
    robe
    0.97
    ly
    0.88
    ward
    0.86
     Bound
    0.81
    ness
    0.80
    wards
    0.79
     Compatibility
    0.78
    bound
    0.74
    Bound
    0.73
    nesses
    0.72
    Activations Density 0.026%

    No Known Activations