© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 2563
    Prev
    Next
    INDEX
    Explanations

    posts or comments on social media profiles

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency, repeated phrases or patterns in text

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

    No Comments

    Negative Logits
    ĸļ
    -0.75
     dotted
    -0.69
     orche
    -0.69
     purs
    -0.67
     pitching
    -0.66
     orchestr
    -0.64
     oun
    -0.64
     Bhar
    -0.64
     dreaded
    -0.63
     fleeing
    -0.63
    POSITIVE LOGITS
    Reply
    1.01
    lol
    0.98
    https
    0.91
    http
    0.87
    Posted
    0.87
    EDIT
    0.84
    Repl
    0.83
    Reviewer
    0.83
    Updated
    0.83
    Spoiler
    0.82
    Activations Density 0.248%

    No Known Activations