© 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. 22481
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or political events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific phonetic sounds or letter patterns

    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
    BILITY
    -0.61
     istg
    -0.60
    76561
    -0.58
     Scion
    -0.57
     deterrence
    -0.57
     NCT
    -0.56
     PID
    -0.56
     reins
    -0.54
     Wanted
    -0.54
     Berks
    -0.54
    POSITIVE LOGITS
    arella
    0.86
    atchewan
    0.73
    estic
    0.72
    hin
    0.70
    iris
    0.67
    adan
    0.67
    bia
    0.67
    raised
    0.67
    oran
    0.67
    oya
    0.66
    Activations Density 0.097%

    No Known Activations