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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 24240
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions, hospitals, and police incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of animal, likely pigs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     awoken
    -0.66
     elevated
    -0.64
     curse
    -0.64
     threat
    -0.63
     cycle
    -0.63
     mon
    -0.62
     obligation
    -0.61
     rebound
    -0.61
     indifferent
    -0.59
     immun
    -0.58
    POSITIVE LOGITS
    igs
    4.84
    ig
    2.05
    igg
    1.55
    IG
    1.34
    igger
    1.17
    igers
    1.14
    ige
    1.12
    igible
    1.05
    igans
    1.05
    iners
    1.01
    Activations Density 0.009%

    No Known Activations