© 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. 9180
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating degree or level for various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparisons or contrasts that highlight surprising or noteworthy characteristics

    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
    dayName
    -0.76
    uum
    -0.74
    renheit
    -0.72
    icide
    -0.71
    nery
    -0.67
    onomic
    -0.66
     whoever
    -0.62
    Jump
    -0.60
     Beetle
    -0.60
    uilding
    -0.59
    POSITIVE LOGITS
     noteworthy
    0.85
     notable
    0.83
    details
    0.81
     irony
    0.80
    noticed
    0.73
     downside
    0.73
     bombshell
    0.72
     importantly
    0.71
     facet
    0.71
    paralle
    0.71
    Activations Density 0.405%

    No Known Activations