© 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. 6-RES-JB
    11. 7678
    Prev
    Next
    INDEX
    Explanations

    instances where the text refers to an individual or group's action or result

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "As a" or similar constructions that express personal perspective or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Els
    -0.85
    andon
    -0.85
    abouts
    -0.78
    bots
    -0.75
    Hamilton
    -0.75
    rences
    -0.72
    metadata
    -0.72
    CHAPTER
    -0.71
    enges
    -0.71
     Jagu
    -0.70
    POSITIVE LOGITS
     result
    1.12
     reminder
    1.09
     consequence
    0.96
     disclaimer
    0.89
     member
    0.88
     standalone
    0.85
     refres
    0.85
     testament
    0.85
     viewer
    0.84
     precaution
    0.82
    Activations Density 0.058%

    No Known Activations