© 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. 9-RES-JB
    11. 6873
    Prev
    Next
    INDEX
    Explanations

    phrases related to truth or honesty

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uled
    -0.67
    capacity
    -0.65
    alian
    -0.64
    ATA
    -0.63
    oyal
    -0.61
    ateur
    -0.59
    OTS
    -0.59
     Rivals
    -0.59
     Pharm
    -0.58
    reciation
    -0.58
    POSITIVE LOGITS
    fulness
    1.43
    fully
    1.21
    telling
    1.02
    iness
    1.01
    orial
    0.87
    ful
    0.87
     serum
    0.85
     seeker
    0.84
    ulent
    0.81
    seekers
    0.80
    Activations Density 0.036%

    No Known Activations