© 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. 1-RES-JB
    6. 8874
    Prev
    Next
    INDEX
    Explanations

    references to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the end punctuation of a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogy
    -0.92
    emen
    -0.85
    chwitz
    -0.76
    hesda
    -0.71
    aling
    -0.70
     batted
    -0.70
    ©¶æ
    -0.69
    urg
    -0.69
    ettel
    -0.67
    wolves
    -0.65
    POSITIVE LOGITS
    Developer
    0.76
     impatient
    0.72
     Modified
    0.71
    iculty
    0.70
    entity
    0.65
    003
    0.64
    ][/
    0.62
    nm
    0.61
     Tribal
    0.61
     impat
    0.60
    Activations Density 0.000%

    No Known Activations