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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 23099
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations or directions

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

    No Comments

    Negative Logits
    apego
    -0.87
    encer
    -0.71
    rogens
    -0.70
    HCR
    -0.68
    ourge
    -0.68
    paio
    -0.68
    uristic
    -0.68
     bearer
    -0.68
    umbnails
    -0.67
     label
    -0.67
    POSITIVE LOGITS
     circles
    0.83
     mode
    0.82
     contexts
    0.81
     increments
    0.80
     manner
    0.80
     context
    0.76
     guise
    0.75
     form
    0.73
     Heights
    0.72
     fashion
    0.72
    Activations Density 0.472%

    No Known Activations