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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18262
    Prev
    Next
    INDEX
    Explanations

    phrases related to blindness or being oblivious

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference a lack of awareness or understanding, often indicated by the term "blind" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.88
    ICAN
    -0.73
     Heights
    -0.71
     Occupations
    -0.71
    andum
    -0.69
    ickr
    -0.69
    afort
    -0.66
    ————
    -0.65
     accur
    -0.63
    akeru
    -0.63
    POSITIVE LOGITS
    fold
    1.50
    sight
    1.39
    sided
    1.34
    ingly
    1.18
    sighted
    1.07
    blind
    1.06
    eyed
    1.06
    spot
    1.05
    legged
    0.90
    side
    0.89
    Activations Density 0.053%

    No Known Activations