© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2590
    Prev
    Next
    INDEX
    Explanations

    pieces of text related to data frames or coding terminology

    oai_token-act-pair · gpt-3.5-turbo

    code-related terms and data management concepts

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.85
    EStream
    -0.83
    ãĥ¯ãĥ³
    -0.80
    ãĥīãĥ©ãĤ´ãĥ³
    -0.80
     pione
    -0.77
    ñ
    -0.72
     è£ıè
    -0.71
    è£ħ
    -0.71
    é¾į
    -0.69
    ModLoader
    -0.68
    POSITIVE LOGITS
    iencies
    0.73
    lege
    0.69
    etry
    0.69
    erers
    0.69
    SPONSORED
    0.68
    irs
    0.68
    nam
    0.67
    ]);
    0.66
    iffe
    0.65
    ises
    0.65
    Activations Density 0.329%

    No Known Activations