© 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. 3-RES-JB
    11. 6574
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific entity named "Caboclo."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity named "Cab."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTWARE
    -0.88
    DonaldTrump
    -0.84
    ãĥĦ
    -0.82
    ãģį
    -0.75
    iband
    -0.74
    ODUCT
    -0.73
    ãĤ´ãĥ³
    -0.73
    hirt
    -0.72
    ãĥĩãĤ£
    -0.68
    Downloadha
    -0.68
    POSITIVE LOGITS
    ulic
    0.96
     Cab
    0.88
    aret
    0.87
    anas
    0.82
    oline
    0.81
    ez
    0.80
    abal
    0.78
    ulent
    0.78
    olina
    0.78
    ram
    0.75
    Activations Density 0.014%

    No Known Activations