© 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. 6-RES-JB
    6. 14838
    Prev
    Next
    INDEX
    Explanations

    entities or terms related to medical conditions or anatomical descriptors that end with the suffix ``rit``

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, likely a notable figure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.89
    ¶ħ
    -0.83
    ĨĴ
    -0.83
    ¥ŀ
    -0.76
    «ĺ
    -0.75
    ARR
    -0.67
    ĻĤ
    -0.65
    FG
    -0.65
    POS
    -0.65
    nect
    -0.64
    POSITIVE LOGITS
    ual
    1.07
    chard
    1.02
    ravel
    0.94
    chet
    0.92
    sch
    0.90
    ters
    0.87
    tered
    0.86
    sis
    0.86
    ually
    0.85
    s
    0.85
    Activations Density 0.017%

    No Known Activations