Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14240
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to a specific theme, potentially a title or name of something, like 'Staplemony'

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "ony" and "omy."

    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
    ational
    -0.74
    ifier
    -0.70
    ivist
    -0.66
    animous
    -0.66
    izable
    -0.63
    IBLE
    -0.60
    ifying
    -0.59
     elig
    -0.58
    aciously
    -0.58
     productive
    -0.57
    POSITIVE LOGITS
    tsky
    1.06
    cling
    1.05
    lene
    1.01
    eah
    1.00
    tons
    1.00
    gdala
    0.99
    tics
    0.99
    stals
    0.97
    chuk
    0.94
    gian
    0.94
    Activations Density 0.145%

    No Known Activations