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. 8717
    Prev
    Next
    INDEX
    Explanations

    city names

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to location or geographic references

    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
    ividual
    -0.50
     allowances
    -0.48
     horizont
    -0.48
    ":[{"
    -0.47
     hindsight
    -0.45
     overload
    -0.45
    azeera
    -0.44
     redundancy
    -0.44
    assian
    -0.43
     undecided
    -0.43
    POSITIVE LOGITS
    ensis
    0.51
    reck
    0.50
    ahu
    0.49
     âĵĺ
    0.48
    âĢİ
    0.47
    orum
    0.46
     Ltd
    0.46
    Corp
    0.45
    orde
    0.44
    eus
    0.44
    Activations Density 1.471%

    No Known Activations