© 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
    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. 21825
    Prev
    Next
    INDEX
    Explanations

    words related to personal opinions and experiences

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal opinion

    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
    edient
    -0.71
     externalToEVAOnly
    -0.66
    escription
    -0.63
    tnc
    -0.61
    redients
    -0.61
    aligned
    -0.60
    etsk
    -0.60
    styles
    -0.60
    arching
    -0.59
    aughtered
    -0.59
    POSITIVE LOGITS
     mean
    1.32
     dunno
    1.30
    'm
    1.29
     swear
    1.23
     suppose
    1.23
     guess
    1.21
     presume
    1.13
     reckon
    1.10
     assure
    1.10
     guarantee
    1.03
    Activations Density 0.165%

    No Known Activations