© 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. 9-RES-JB
    11. 13499
    Prev
    Next
    INDEX
    Explanations

    phrases related to similarity or affinity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inas
    -0.72
     Palestin
    -0.70
     destro
    -0.69
     millenn
    -0.65
     enthusi
    -0.64
    Catal
    -0.60
    arthy
    -0.58
    elfare
    -0.58
    uliffe
    -0.58
    PATH
    -0.57
    POSITIVE LOGITS
    lihood
    2.19
    liest
    1.41
    lier
    1.22
    liness
    1.22
    ability
    1.18
     minded
    1.18
    minded
    1.16
    able
    0.96
    joy
    0.88
    ably
    0.80
    Activations Density 0.050%

    No Known Activations