© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a subject or entity within a context

    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
    tarians
    -0.69
     Occupations
    -0.69
    reads
    -0.65
    ormons
    -0.63
    clinton
    -0.60
    oscope
    -0.59
    tones
    -0.59
    aughs
    -0.59
    sbm
    -0.59
     Cosponsors
    -0.59
    POSITIVE LOGITS
     notoriously
    1.21
     dreaded
    1.21
     hitherto
    1.20
     increasingly
    1.19
     elusive
    1.17
     enigmatic
    1.14
     comparatively
    1.13
     venerable
    1.13
     fearsome
    1.12
     hugely
    1.09
    Activations Density 0.855%

    No Known Activations