© 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. 4-RES-JB
    11. 579
    Prev
    Next
    INDEX
    Explanations

    ambiguous statements implying uncertainty or variety in options

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "even," often suggesting an emphasis or consideration of additional possibilities

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

    No Comments

    Negative Logits
    othy
    -0.78
    aim
    -0.77
    rend
    -0.73
    cent
    -0.69
    plex
    -0.66
    _-
    -0.66
    idelines
    -0.65
     Nare
    -0.64
    oder
    -0.64
    Buff
    -0.64
    POSITIVE LOGITS
     remotely
    0.92
    romeda
    0.69
     speculate
    0.68
     uncond
    0.67
     moderately
    0.65
     outright
    0.64
    handedly
    0.63
     indirectly
    0.62
     fanc
    0.62
    osponsors
    0.61
    Activations Density 0.043%

    No Known Activations