Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12469
    Prev
    Next
    INDEX
    Explanations

    phrases or words relating to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or proper noun related to individuals or entities, primarily focusing on the term "Guevara."

    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
     mids
    -0.64
    RESULTS
    -0.64
     OD
    -0.61
     Arctic
    -0.60
     openness
    -0.60
     readiness
    -0.60
     limiting
    -0.59
     diary
    -0.59
     masculine
    -0.59
    ifax
    -0.58
    POSITIVE LOGITS
    ue
    1.27
    lla
    1.05
    ues
    0.99
    llo
    0.98
    UE
    0.97
    lect
    0.91
    pee
    0.88
    uer
    0.87
    ued
    0.84
    pees
    0.83
    Activations Density 0.010%

    No Known Activations