© 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. 1-RES-JB
    11. 20620
    Prev
    Next
    INDEX
    Explanations

    words related to internet relay chat (IRC)

    oai_token-act-pair · gpt-3.5-turbo

    references to Internet Relay Chat (IRC) and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.75
     stride
    -0.69
     aid
    -0.68
     prompts
    -0.66
    ãĤ©
    -0.64
     cane
    -0.64
     Arbor
    -0.64
     Rite
    -0.63
    bridge
    -0.63
    ãĥ³ãĤ¸
    -0.63
    POSITIVE LOGITS
    irc
    1.25
    ###
    0.99
    ategory
    0.97
    gypt
    0.87
    ##
    0.84
    ession
    0.84
    onda
    0.84
    krit
    0.82
    bestos
    0.82
    onson
    0.81
    Activations Density 0.013%

    No Known Activations