© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 12820
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaking free or escaping a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to escaping or breaking free from situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vetoed
    -0.68
     postp
    -0.67
     banished
    -0.66
     phased
    -0.62
     priorit
    -0.62
     til
    -0.61
     Galile
    -0.60
    atto
    -0.59
     parted
    -0.58
     postponed
    -0.58
    POSITIVE LOGITS
    å§
    0.70
    ymes
    0.70
    ochet
    0.70
    dden
    0.69
    Sax
    0.68
    ydia
    0.66
    taining
    0.63
     rhythm
    0.62
    ð
    0.62
    Fish
    0.61
    Activations Density 0.076%

    No Known Activations