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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 23391
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusion or mention of multiple entities or facts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of membership or association in a group or category

    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
     ([
    -0.74
     Period
    -0.74
    bane
    -0.74
    ynthesis
    -0.70
    hiro
    -0.68
    ensis
    -0.67
    cycle
    -0.65
    arden
    -0.65
    mop
    -0.65
    ategory
    -0.65
    POSITIVE LOGITS
     casualties
    1.03
     targets
    1.02
     beneficiaries
    1.01
     findings
    0.99
     recipients
    0.98
     surprises
    0.95
     topics
    0.94
     dozen
    0.89
     plaintiffs
    0.89
     revelations
    0.89
    Activations Density 0.182%

    No Known Activations