© 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. 7-RES-JB
    11. 7795
    Prev
    Next
    INDEX
    Explanations

    actions or events indicated by the word "then"

    oai_token-act-pair · gpt-3.5-turbo

    the word "then" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toe
    -0.61
     Presence
    -0.61
    mad
    -0.60
     Bie
    -0.60
    crazy
    -0.59
     belief
    -0.58
     competence
    -0.57
     impossibility
    -0.57
    ting
    -0.57
     MAD
    -0.56
    POSITIVE LOGITS
     proceeded
    1.34
     proceed
    1.00
     proceeds
    0.94
     promptly
    0.89
     transitioned
    0.87
    ©¶æ
    0.82
     instructed
    0.77
    veland
    0.76
     recons
    0.76
    ļéĨĴ
    0.76
    Activations Density 0.047%

    No Known Activations