© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    6. 6058
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and proceedings

    oai_token-act-pair · gpt-3.5-turbo

    words related to 'iment' and its variations, indicating a focus on suffixes pertaining to processes or states, particularly in a scientific or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teen
    -0.74
    ECD
    -0.74
    AMS
    -0.70
    ©¶æ
    -0.69
    ILLE
    -0.67
    WHERE
    -0.66
    holder
    -0.65
    PE
    -0.65
    ARD
    -0.65
    å¸
    -0.64
    POSITIVE LOGITS
    iment
    1.24
    opol
    1.14
    ation
    1.05
    iments
    1.01
    ogly
    0.97
    ality
    0.95
    ial
    0.93
    ocre
    0.89
    rait
    0.89
    icip
    0.88
    Activations Density 0.007%

    No Known Activations