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. 9314
    Prev
    Next
    INDEX
    Explanations

    terms indicative of clarity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to clarity and coherence

    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
    hops
    -1.13
    aunts
    -0.91
    lees
    -0.87
    hots
    -0.85
    events
    -0.83
    ifles
    -0.80
     balloons
    -0.79
    rants
    -0.79
    packages
    -0.79
    ummies
    -0.77
    POSITIVE LOGITS
     solution
    1.06
     explanation
    1.01
     approximation
    0.98
     indication
    0.97
     antidote
    0.95
     amount
    0.94
     contender
    0.93
     presence
    0.93
     slate
    0.89
     relationship
    0.89
    Activations Density 0.253%

    No Known Activations