© 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. 24111
    Prev
    Next
    INDEX
    Explanations

    prepositions relating to travel or movement towards a specific location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to," indicating a focus on intentions or actions related to movement or direction

    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
    canon
    -0.65
    ellation
    -0.65
    states
    -0.64
    growth
    -0.62
     Lives
    -0.60
     Changes
    -0.60
    izational
    -0.60
    raining
    -0.58
     Limits
    -0.58
    emin
    -0.58
    POSITIVE LOGITS
     retrieve
    1.22
     await
    1.13
     celebrate
    1.12
     inspect
    1.11
     observe
    1.11
     witness
    1.10
     partake
    1.09
     meet
    1.08
     discuss
    1.08
     investigate
    1.08
    Activations Density 0.110%

    No Known Activations