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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17259
    Prev
    Next
    INDEX
    Explanations

    text related to a specific name or location "Gómez."

    oai_token-act-pair · gpt-3.5-turbo

    the character "ó" and its variations in different 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
    ationally
    -0.68
    ŃĶ
    -0.61
    arios
    -0.60
    othal
    -0.59
    pread
    -0.57
     Pasadena
    -0.57
     compuls
    -0.57
    naires
    -0.57
    ighton
    -0.56
    engers
    -0.56
    POSITIVE LOGITS
    rien
    1.05
    rio
    0.95
    ÃįÃį
    0.93
    ó
    0.89
    ð
    0.89
    s
    0.86
    atl
    0.85
    sa
    0.84
    si
    0.82
    lic
    0.82
    Activations Density 0.027%

    No Known Activations