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. 21414
    Prev
    Next
    INDEX
    Explanations

    instances of references or citations in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of names and years related to various cases and 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
     millenn
    -0.85
    PDATE
    -0.78
     referen
    -0.74
     eleph
    -0.68
     conflic
    -0.68
    acebook
    -0.64
    olester
    -0.63
    ategory
    -0.63
     hormonal
    -0.62
    emetery
    -0.62
    POSITIVE LOGITS
     AFB
    0.81
     Associates
    0.79
     LLP
    0.75
    sch
    0.71
     Consulting
    0.70
     Creek
    0.68
     County
    0.67
    beck
    0.67
     Plain
    0.66
    lees
    0.65
    Activations Density 0.698%

    No Known Activations