© 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. 8-RES-JB
    11. 17211
    Prev
    Next
    INDEX
    Explanations

    statements indicating likelihood or probability of occurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating likelihood or probability

    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
    Cooldown
    -0.77
    cle
    -0.73
    DAQ
    -0.72
     embodiments
    -0.71
    Textures
    -0.70
    urance
    -0.68
    cedented
    -0.68
    holder
    -0.67
    audio
    -0.66
    engineering
    -0.66
    POSITIVE LOGITS
     receive
    1.19
     participate
    1.13
     succeed
    1.12
     be
    1.10
     survive
    1.08
     engage
    1.06
     offend
    1.03
     utilize
    1.02
     indulge
    1.02
     cooperate
    1.01
    Activations Density 0.067%

    No Known Activations