© 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. 24020
    Prev
    Next
    INDEX
    Explanations

    mentions of the telecommunications company "AT&T"

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "AT&T"

    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
    perse
    -0.76
    ingen
    -0.69
    pressure
    -0.66
    haven
    -0.66
    ppelin
    -0.66
     Bosnia
    -0.64
    theless
    -0.64
     pandemonium
    -0.63
     Wanted
    -0.61
    place
    -0.61
    POSITIVE LOGITS
    rix
    1.05
    tiny
    1.05
    &
    1.01
    ARI
    1.01
    Ms
    1.00
    mega
    0.98
    TAIN
    0.94
    OM
    0.92
    TR
    0.90
    LAN
    0.90
    Activations Density 0.016%

    No Known Activations