© 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. 20339
    Prev
    Next
    INDEX
    Explanations

    keywords related to requesting and retrieving resources or data

    oai_token-act-pair · gpt-3.5-turbo
    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
    ŃĶ
    -0.78
    ©¶æ
    -0.78
    VIDIA
    -0.72
     Beir
    -0.68
    \\\\\\\\
    -0.67
    ĸļ士
    -0.67
    ailability
    -0.66
     exting
    -0.66
    vertising
    -0.66
    è¦ļéĨĴ
    -0.65
    POSITIVE LOGITS
     )
    0.63
     ),
    0.59
     acronym
    0.59
     ).
    0.58
     ):
    0.58
     .
    0.58
     ,
    0.56
     abbre
    0.55
     RPM
    0.54
     rpm
    0.53
    Activations Density 0.067%

    No Known Activations