© 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. 8-RES-JB
    11. 1153
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or events that involve movement or change

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and phrases that indicate uncertainty or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agna
    -0.68
    pherd
    -0.67
    ©¶æ¥µ
    -0.65
     subclass
    -0.65
    isans
    -0.64
    igenous
    -0.63
    iversal
    -0.62
    iosyncr
    -0.62
     compiled
    -0.60
     professors
    -0.60
    POSITIVE LOGITS
    izont
    0.88
     Arrows
    0.77
     Collider
    0.73
    literally
    0.72
     seams
    0.70
    quit
    0.69
     Repeat
    0.68
    illation
    0.68
     stairs
    0.68
     Leaves
    0.67
    Activations Density 0.914%

    No Known Activations