© 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. 2769
    Prev
    Next
    INDEX
    Explanations

    phrases related to being informed or instructed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "was told."

    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
    aho
    -0.68
    adesh
    -0.67
    ivot
    -0.66
    ent
    -0.64
    ADD
    -0.63
     Confeder
    -0.63
    vous
    -0.61
    gain
    -0.60
    knife
    -0.59
    entials
    -0.59
    POSITIVE LOGITS
     orally
    0.84
     by
    0.84
     beforehand
    0.78
    tale
    0.71
     repeatedly
    0.70
     wrongly
    0.69
     goodbye
    0.68
     timet
    0.66
     tales
    0.66
    rone
    0.66
    Activations Density 0.038%

    No Known Activations