© 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. 9-RES-JB
    11. 16346
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    frequency of a specific letter or character pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samar
    -0.65
     Skydragon
    -0.60
     Hawaii
    -0.58
     RAD
    -0.57
     ATL
    -0.57
     Laurent
    -0.56
     MUS
    -0.56
     tra
    -0.53
     Kaf
    -0.53
     OM
    -0.53
    POSITIVE LOGITS
    s
    0.83
    tarian
    0.82
    estic
    0.77
    t
    0.77
    scl
    0.75
    ifer
    0.74
    swer
    0.72
    ity
    0.70
    ific
    0.69
    ief
    0.69
    Activations Density 0.245%

    No Known Activations