© 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. 0-RES-JB
    11. 4122
    Prev
    Next
    INDEX
    Explanations

    words related to the company AT&T

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "AT&T" brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zanne
    -0.81
    ÄŁ
    -0.75
    cephal
    -0.69
     Flask
    -0.66
    mber
    -0.65
    iour
    -0.65
    ixir
    -0.63
    helm
    -0.63
    âĢİ
    -0.63
    ember
    -0.63
    POSITIVE LOGITS
     AT
    3.65
    AT
    1.85
     ATM
    1.75
     DOT
    1.37
     AS
    1.34
     ATI
    1.31
     Verizon
    1.22
     BY
    1.20
     Sprint
    1.19
     BT
    1.18
    Activations Density 0.014%

    No Known Activations