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. 0-RES-JB
    6. 1031
    Prev
    Next
    INDEX
    Explanations

    phrases related to structure and service

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structural organization and service references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romeda
    -0.90
     Crusher
    -0.82
    sonian
    -0.78
     Nebula
    -0.76
    milo
    -0.71
    oodle
    -0.70
    edition
    -0.70
     Andromeda
    -0.69
    adena
    -0.69
    arian
    -0.68
    POSITIVE LOGITS
    YP
    1.96
     struct
    1.89
     serv
    1.76
     Jackets
    1.36
     voic
    1.23
     rout
    1.18
    Struct
    1.14
     buoy
    1.07
    ownt
    1.04
     recapt
    1.03
    Activations Density 0.053%

    No Known Activations