Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23652
    Prev
    Next
    INDEX
    Explanations

    phrases related to falling from heights or structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of falling or related actions

    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
    uncture
    -0.75
    ffect
    -0.74
    PN
    -0.72
    urg
    -0.70
    ecided
    -0.70
    ochemistry
    -0.70
    matter
    -0.70
     handwriting
    -0.65
    alysis
    -0.65
     fingerprint
    -0.65
    POSITIVE LOGITS
     cliffs
    1.46
     cliff
    1.33
     tallest
    1.29
     stairs
    1.27
     skysc
    1.26
     ceilings
    1.24
     ceiling
    1.17
     mast
    1.16
     roofs
    1.15
     scaff
    1.15
    Activations Density 0.266%

    No Known Activations