© 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. 3-RES-JB
    11. 15141
    Prev
    Next
    INDEX
    Explanations

    phrases related to saving or rescuing something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of saving lives or preventing harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Intern
    -0.67
    aches
    -0.63
    naire
    -0.61
     elder
    -0.60
    yond
    -0.60
    auer
    -0.60
     inventive
    -0.59
    quartered
    -0.58
     adapter
    -0.58
     adapters
    -0.58
    POSITIVE LOGITS
    Save
    0.99
    saving
    0.83
     Save
    0.82
     save
    0.78
    osit
    0.78
     Saving
    0.76
    anza
    0.75
    éĹĺ
    0.75
    aret
    0.73
    save
    0.73
    Activations Density 0.018%

    No Known Activations