© 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
    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. 13917
    Prev
    Next
    INDEX
    Explanations

    phrases related to companies or organizations emphasizing or highlighting certain qualities or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe companies or organizations and how they present or define themselves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ]}
    -0.67
    <
    -0.65
    wagen
    -0.64
     respectively
    -0.64
    idian
    -0.63
    anyon
    -0.60
    çİĭ
    -0.60
    aley
    -0.58
    $.
    -0.57
    laughter
    -0.57
    POSITIVE LOGITS
     its
    2.13
     itself
    2.06
     Its
    1.84
    Its
    1.70
     ITS
    1.63
    its
    0.89
     internally
    0.60
     cohesion
    0.59
     adherents
    0.59
    alus
    0.58
    Activations Density 1.244%

    No Known Activations