© 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. 7-RES-JB
    11. 1799
    Prev
    Next
    INDEX
    Explanations

    objects or entities that are described as being at the top or uppermost level of a hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hierarchical rankings or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.75
    ndum
    -0.66
    interrupted
    -0.60
    rities
    -0.59
    urgy
    -0.59
    ryu
    -0.57
     Paraly
    -0.55
     tears
    -0.55
    tm
    -0.55
    ãĤ¶
    -0.54
    POSITIVE LOGITS
     earners
    0.79
     drawer
    0.77
     notch
    0.71
    ranking
    0.69
    Tier
    0.69
    draw
    0.68
    lining
    0.67
    nings
    0.66
     contender
    0.65
     priority
    0.64
    Activations Density 0.082%

    No Known Activations