© 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. 11095
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual impairment or not being able to see

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "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 @ 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
    xit
    -0.82
    ICAN
    -0.75
    andum
    -0.73
    ickr
    -0.72
    OPLE
    -0.71
    afort
    -0.70
     Heights
    -0.69
    cially
    -0.66
    akeru
    -0.66
     Forth
    -0.65
    POSITIVE LOGITS
    fold
    1.52
    sided
    1.41
    sight
    1.35
    ingly
    1.19
    spot
    1.08
    sighted
    1.03
    eyed
    1.00
    blind
    0.98
    jah
    0.90
    side
    0.90
    Activations Density 0.031%

    No Known Activations