© 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. 8-RES-JB
    11. 7050
    Prev
    Next
    INDEX
    Explanations

    words related to speculation or guessing

    oai_token-act-pair · gpt-3.5-turbo

    words related to surrender or yielding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icals
    -0.81
    opathic
    -0.79
     Pax
    -0.67
    ICAL
    -0.66
    arians
    -0.65
     Dynamics
    -0.65
     pathology
    -0.63
    imore
    -0.62
    opathy
    -0.62
     portfolios
    -0.61
    POSITIVE LOGITS
    mounted
    1.13
    fer
    0.93
    charge
    0.92
    mount
    0.92
    noon
    0.86
    tro
    0.85
    lim
    0.84
    sur
    0.83
    saw
    0.82
    clair
    0.81
    Activations Density 0.026%

    No Known Activations