© 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. 8-RES-JB
    11. 17253
    Prev
    Next
    INDEX
    Explanations

    names related to "Har"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the character string "Har"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.86
    eers
    -0.72
     Tone
    -0.68
    URES
    -0.66
    UCT
    -0.64
    anwhile
    -0.64
    uyomi
    -0.63
     semantics
    -0.63
    代
    -0.62
    ĸļ
    -0.62
    POSITIVE LOGITS
    assment
    1.13
    vard
    1.08
    riers
    1.06
    rod
    1.03
    rier
    1.02
    rim
    0.99
    ried
    0.96
    rah
    0.95
    poons
    0.94
    rowing
    0.94
    Activations Density 0.023%

    No Known Activations