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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 16667
    Prev
    Next
    INDEX
    Explanations

    phrases starting with a time expression followed by a verb in present continuous tense

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enary
    -0.77
    orem
    -0.73
    uber
    -0.69
    onym
    -0.67
    ahu
    -0.66
    robe
    -0.65
    irc
    -0.65
    ocl
    -0.65
    irie
    -0.63
    ery
    -0.63
    POSITIVE LOGITS
     albeit
    1.29
     although
    1.25
     though
    1.18
     namely
    1.15
     however
    1.14
     especially
    1.10
     whereas
    1.01
     including
    1.01
     but
    1.00
     particularly
    0.94
    Activations Density 0.568%

    No Known Activations