© 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. 22526
    Prev
    Next
    INDEX
    Explanations

    words related to panoramic views or scenes

    oai_token-act-pair · gpt-3.5-turbo

    references to panoramic views

    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
     Intent
    -0.64
     acquaintance
    -0.59
    itability
    -0.59
     Norn
    -0.58
     Remain
    -0.57
     Qiao
    -0.57
     puppy
    -0.56
     Intercept
    -0.55
     AQ
    -0.54
     Naj
    -0.54
    POSITIVE LOGITS
    acea
    1.51
    orama
    1.35
    handler
    1.24
    handle
    1.20
    zers
    1.13
    ning
    1.13
    ache
    1.13
    tera
    1.10
    asonic
    1.08
    handled
    1.08
    Activations Density 0.032%

    No Known Activations