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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17744
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'starting' in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles in sports or theatrical productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utics
    -0.98
    atism
    -0.87
    akespeare
    -0.82
     Retrieved
    -0.78
    alach
    -0.78
    ascript
    -0.77
    ynthesis
    -0.77
    utical
    -0.76
    atche
    -0.75
    olia
    -0.74
    POSITIVE LOGITS
     trio
    1.03
     group
    0.94
     lineup
    0.88
     line
    0.85
     ones
    0.84
     leg
    0.82
     party
    0.82
     panel
    0.81
    most
    0.81
     challenger
    0.79
    Activations Density 0.193%

    No Known Activations