© 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. 17131
    Prev
    Next
    INDEX
    Explanations

    elements related to physical surroundings and settings, particularly with descriptive details

    oai_token-act-pair · gpt-3.5-turbo

    descriptive elements related to visual aesthetics and scenery

    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
     Firstly
    -0.77
    Firstly
    -0.76
    emort
    -0.74
    ccording
    -0.70
     Tycoon
    -0.67
    ificantly
    -0.66
    Secondly
    -0.66
    Additionally
    -0.65
    ENTION
    -0.65
     Specifically
    -0.64
    POSITIVE LOGITS
     perched
    1.19
     draped
    1.18
     dotted
    1.17
     adorned
    1.16
     towering
    1.12
     shrouded
    1.11
     illuminating
    1.11
     dangling
    1.10
     silhou
    1.09
     disg
    1.07
    Activations Density 0.394%

    No Known Activations