© 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. 2-RES-JB
    11. 18396
    Prev
    Next
    INDEX
    Explanations

    the word "possible" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    discussions about the concept of possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bane
    -1.01
    cipline
    -0.82
    cipl
    -0.82
    mpire
    -0.76
    masters
    -0.76
    rix
    -0.75
    oton
    -0.75
    ogie
    -0.74
    OVA
    -0.72
    bey
    -0.69
    POSITIVE LOGITS
     feas
    0.78
     embodiments
    0.75
     00000000
    0.74
    soDeliveryDate
    0.69
     reversible
    0.68
     defect
    0.68
     NK
    0.68
     HRC
    0.68
    ossibility
    0.66
    DragonMagazine
    0.66
    Activations Density 0.023%

    No Known Activations