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. 7-RES-JB
    6. 24187
    Prev
    Next
    INDEX
    Explanations

    Phrases related to knowledge or awareness of specific information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to knowledge and awareness of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igsaw
    -0.75
    phabet
    -0.68
    oples
    -0.67
     rite
    -0.67
    erion
    -0.66
     reunion
    -0.66
    onite
    -0.66
     rejuven
    -0.66
    orative
    -0.65
     renaissance
    -0.64
    POSITIVE LOGITS
     wrongdoing
    1.09
     beforehand
    0.89
     misconduct
    0.88
     Blumenthal
    0.79
    noon
    0.75
    OTAL
    0.74
    REDACTED
    0.73
    DERR
    0.72
     alleged
    0.70
     irregularities
    0.70
    Activations Density 0.149%

    No Known Activations