© 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. 2-RES-JB
    11. 23686
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe paths or methods of accomplishing tasks

    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
    uster
    -0.77
    usters
    -0.76
    encer
    -0.75
    incinn
    -0.66
    anmar
    -0.65
    icio
    -0.65
     Gru
    -0.64
    grave
    -0.63
    akov
    -0.63
    encers
    -0.63
    POSITIVE LOGITS
    fare
    1.06
    finding
    0.92
    point
    0.89
    ward
    0.87
    forward
    0.74
    aterasu
    0.73
     WAY
    0.73
    points
    0.72
     Judaism
    0.71
    drive
    0.71
    Activations Density 0.070%

    No Known Activations