© 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. 11-RES-JB
    11. 16595
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements and declarations

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixme
    -0.73
    brates
    -0.72
     Liberties
    -0.67
    stood
    -0.66
    =-=-=-=-
    -0.65
    iture
    -0.65
     Subtle
    -0.63
    asured
    -0.63
    enment
    -0.63
    udos
    -0.63
    POSITIVE LOGITS
     quitting
    1.20
     abandoning
    1.19
     withdrawing
    1.16
     suspending
    1.12
     cance
    1.10
     dropping
    1.07
     retiring
    1.06
     disband
    1.06
     going
    1.05
     shutting
    1.03
    Activations Density 0.187%

    No Known Activations