© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 6085
    Prev
    Next
    INDEX
    Explanations

    personal names with the letter 'h'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'h' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.75
    eers
    -0.70
     Clicker
    -0.70
    aution
    -0.70
    eering
    -0.68
    e
    -0.62
     fixtures
    -0.62
     mosqu
    -0.61
     flush
    -0.61
     fixation
    -0.60
    POSITIVE LOGITS
    ythm
    1.19
    agen
    1.16
    ulhu
    1.15
    ofer
    1.09
    orses
    1.09
    ollow
    1.08
    ouston
    1.07
    ilde
    1.06
    atever
    1.05
    ackers
    0.99
    Activations Density 0.039%

    No Known Activations