© 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. 7-RES-JB
    11. 13479
    Prev
    Next
    INDEX
    Explanations

    instances of the word "back" in a sentence where something is being returned or restored

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of returning or giving something back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entric
    -0.70
    ities
    -0.64
    izo
    -0.62
    oit
    -0.61
    ision
    -0.61
     viz
    -0.61
    enture
    -0.60
    uary
    -0.60
     coefficient
    -0.59
     understatement
    -0.59
    POSITIVE LOGITS
    dated
    1.15
    packs
    1.00
    fires
    0.98
    doors
    0.97
    fired
    0.96
    haul
    0.89
    stab
    0.86
    tracking
    0.84
    trace
    0.83
    gam
    0.83
    Activations Density 0.044%

    No Known Activations