© 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. 8-RES-JB
    11. 18701
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sche†" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sche" and its variations in the text

    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
     eleph
    -0.82
    ORED
    -0.80
    Downloadha
    -0.77
    INGTON
    -0.71
     tremend
    -0.68
    etheless
    -0.67
     Taiwanese
    -0.64
    å°Ĩ
    -0.64
     adore
    -0.64
     needless
    -0.61
    POSITIVE LOGITS
    dule
    1.26
    fter
    1.05
    infeld
    1.03
    ller
    1.01
    cker
    0.96
    lling
    0.96
    tto
    0.95
    ven
    0.95
    ppo
    0.93
    eta
    0.93
    Activations Density 0.031%

    No Known Activations