© 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. 10-RES-JB
    11. 12837
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration or investigation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explore" and its variations, indicating a focus on exploration and examination of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAY
    -0.64
    pora
    -0.62
    chal
    -0.61
    wait
    -0.59
    grass
    -0.58
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.57
     household
    -0.57
     petitions
    -0.56
     sem
    -0.56
    ï¸
    -0.56
    POSITIVE LOGITS
    oit
    1.43
    oded
    1.40
    oding
    1.40
    icit
    1.39
    osion
    1.36
    ained
    1.36
    orers
    1.31
    aining
    1.27
    ainer
    1.27
    oration
    1.21
    Activations Density 0.022%

    No Known Activations