© 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. 10-RES-JB
    6. 17499
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to oneself or others, and verbs indicating a change or current state of being

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements about identity and self-perception

    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
    arya
    -0.74
     breeze
    -0.68
    artifacts
    -0.66
     margin
    -0.61
     clearance
    -0.60
     hazard
    -0.60
     Checking
    -0.59
     Clever
    -0.56
    elsius
    -0.56
    ragon
    -0.55
    POSITIVE LOGITS
    Reloaded
    0.70
     profess
    0.68
    uably
    0.68
     pretended
    0.64
    rir
    0.64
    rencies
    0.63
    Self
    0.62
    uer
    0.61
     portrays
    0.60
     Become
    0.59
    Activations Density 0.115%

    No Known Activations