© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17218
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating occurrences or events that have taken place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Property
    -0.66
    stable
    -0.57
    involved
    -0.56
    theless
    -0.55
    nor
    -0.53
    Job
    -0.52
    sf
    -0.52
     puppet
    -0.51
    roots
    -0.51
    stood
    -0.50
    POSITIVE LOGITS
     courtesy
    1.12
     when
    0.85
     shortly
    0.84
     via
    0.84
    when
    0.78
     thanks
    0.77
     midway
    0.75
     during
    0.72
     pouring
    0.72
     amidst
    0.69
    Activations Density 0.056%

    No Known Activations