© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity named "Claudio Ranieri."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific person or entity abbreviated as "Cl"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.81
     è£ı
    -0.75
    æĢ
    -0.72
    ãĥĨãĤ£
    -0.69
    manship
    -0.69
    çͰ
    -0.68
    ãĥį
    -0.68
    shine
    -0.67
    çĽ
    -0.66
    ELL
    -0.66
    POSITIVE LOGITS
    iff
    1.08
    ipper
    1.07
    osures
    1.04
    iffs
    1.04
    oser
    1.02
    othes
    0.99
    iffe
    0.98
    osure
    0.96
    imb
    0.95
    ients
    0.90
    Activations Density 0.008%

    No Known Activations