© 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. 0-RES-JB
    11. 22672
    Prev
    Next
    INDEX
    Explanations

    words related to actions of ingesting or consuming

    oai_token-act-pair · gpt-3.5-turbo

    words associated with various forms of sexual exploitation or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magazine
    -0.66
     plate
    -0.59
     associations
    -0.58
     design
    -0.58
     mask
    -0.58
     screw
    -0.58
     handic
    -0.57
     association
    -0.57
     shop
    -0.57
     podcasts
    -0.56
    POSITIVE LOGITS
    ested
    4.35
    esting
    2.98
    ests
    2.36
    estation
    2.19
    est
    1.74
    EST
    1.60
    esters
    1.38
    esta
    1.31
    ester
    1.21
    uned
    1.07
    Activations Density 0.007%

    No Known Activations