© 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. 8-RES-JB
    11. 6372
    Prev
    Next
    INDEX
    Explanations

    phrases indicating someone's rise to fame or power

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rising to prominence or status

    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
    going
    -0.61
    eele
    -0.60
     leases
    -0.60
    ng
    -0.59
    riger
    -0.58
     mouths
    -0.57
    tenance
    -0.57
     ðŁij
    -0.56
     drained
    -0.55
     severed
    -0.54
    POSITIVE LOGITS
     prominence
    1.13
     heights
    0.94
     sidx
    0.90
     maturity
    0.82
     notoriety
    0.73
     encompass
    0.72
     adulthood
    0.71
     become
    0.71
    ENTS
    0.70
    pless
    0.70
    Activations Density 0.099%

    No Known Activations