© 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. 2-RES-JB
    11. 18981
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms such as "cabs", "absurd", and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    the word "cabs" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frey
    -0.70
     Nanto
    -0.66
    ERAL
    -0.62
     Maker
    -0.62
     Correct
    -0.62
    piece
    -0.59
     COUR
    -0.59
    onymous
    -0.58
     Honour
    -0.58
     Reaction
    -0.58
    POSITIVE LOGITS
    abs
    1.02
    orb
    0.98
    poons
    0.95
    poon
    0.88
    acus
    0.88
    itol
    0.86
    hips
    0.86
    ibilities
    0.85
    yip
    0.82
    ayers
    0.82
    Activations Density 0.007%

    No Known Activations