© 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. 6862
    Prev
    Next
    INDEX
    Explanations

    phrases related to performing actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions and their execution or performance in various contexts

    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
     attRot
    -0.60
    SPONSORED
    -0.60
    rem
    -0.54
    arks
    -0.54
    olls
    -0.53
    esthetic
    -0.51
    fed
    -0.51
    Ku
    -0.51
    iru
    -0.50
    /?
    -0.50
    POSITIVE LOGITS
     anonymously
    1.27
     separately
    1.21
     via
    1.17
     indirectly
    1.11
     electronically
    1.10
     manually
    1.07
     outdoors
    1.04
     remotely
    1.02
     WITHOUT
    1.01
     independently
    1.01
    Activations Density 0.810%

    No Known Activations