© 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. 3-RES-JB
    11. 7267
    Prev
    Next
    INDEX
    Explanations

    words related to facing challenges or difficulties

    oai_token-act-pair · gpt-3.5-turbo

    references to difficulties or challenges faced by individuals or groups

    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
    entric
    -0.78
    alty
    -0.78
    omin
    -0.72
    collar
    -0.70
    velop
    -0.67
    ovo
    -0.66
    achers
    -0.65
    lav
    -0.65
    nesty
    -0.64
    cription
    -0.64
    POSITIVE LOGITS
     miser
    0.87
     struggling
    0.78
    hirt
    0.76
     struggled
    0.76
    icago
    0.71
    acus
    0.71
     facing
    0.68
     strugg
    0.67
    iana
    0.66
    wcs
    0.65
    Activations Density 0.017%

    No Known Activations