© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    terms related to proper names or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names

    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
    )."
    -0.79
    pic
    -0.70
    ©¶æ¥µ
    -0.65
    ]."
    -0.64
    bart
    -0.64
     Ic
    -0.63
    fu
    -0.63
     Bers
    -0.62
    Calif
    -0.62
     Kab
    -0.62
    POSITIVE LOGITS
     consists
    0.78
     refers
    0.65
     specializes
    0.65
     subsystem
    0.63
     civilization
    0.61
     comprises
    0.61
     contains
    0.60
     consist
    0.60
     composed
    0.59
     consisted
    0.59
    Activations Density 0.627%

    No Known Activations