© 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. 4938
    Prev
    Next
    INDEX
    Explanations

    commentary or analysis about various topics or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to investigative research and critical analysis in literature and culture

    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
     RAID
    -0.78
     Maintenance
    -0.75
    Speed
    -0.75
     Parking
    -0.74
     Facilities
    -0.73
    SourceFile
    -0.72
    adelphia
    -0.71
    yip
    -0.70
     Pwr
    -0.70
     Manufacturer
    -0.68
    POSITIVE LOGITS
     scholarly
    1.25
     anthropology
    1.15
     journalistic
    1.13
     contemporary
    1.12
     literary
    1.08
     insights
    1.07
     essays
    1.07
     prophetic
    1.06
     histor
    1.06
     autobi
    1.03
    Activations Density 1.202%

    No Known Activations