© 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. 8-RES-JB
    11. 20194
    Prev
    Next
    INDEX
    Explanations

    dates and locations from news articles

    oai_token-act-pair · gpt-3.5-turbo

    dates and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berries
    -0.65
     hiber
    -0.61
     typo
    -0.60
     impulse
    -0.59
     tunes
    -0.59
     dotted
    -0.59
    bench
    -0.58
     maiden
    -0.58
     fools
    -0.58
     sucker
    -0.57
    POSITIVE LOGITS
     REUTERS
    1.02
     Reuters
    0.72
    UTERS
    0.69
     ASS
    0.66
     Mandatory
    0.65
     Picture
    0.65
     Sponsor
    0.63
    Actor
    0.62
    AFP
    0.61
    Reuters
    0.61
    Activations Density 0.165%

    No Known Activations