© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1712
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific entity or community named "Fam" with varying levels of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to family-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gravy
    -0.72
    TAIN
    -0.68
     downt
    -0.67
     undert
    -0.66
     Thornton
    -0.66
    arson
    -0.63
    ._
    -0.63
    rose
    -0.62
     slur
    -0.62
    negative
    -0.62
    POSITIVE LOGITS
     Fam
    4.18
     fam
    2.06
     FAM
    1.53
    fam
    1.39
     NES
    1.18
     Atl
    1.05
     Persona
    1.00
     Caf
    0.98
     Nintendo
    0.97
     Anim
    0.93
    Activations Density 0.020%

    No Known Activations