© 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. 10-RES-JB
    11. 24376
    Prev
    Next
    INDEX
    Explanations

    instances where credit, recognition, praise, or accolades are given

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recognition and credit for achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rir
    -0.66
     weeds
    -0.61
    aple
    -0.60
    eworks
    -0.57
     depths
    -0.56
    Ó
    -0.55
    idth
    -0.55
     Lies
    -0.55
    dimension
    -0.55
     tensions
    -0.55
    POSITIVE LOGITS
     from
    0.90
     deserved
    0.90
     bestowed
    0.87
     thanks
    0.81
     courtesy
    0.77
    hum
    0.76
    âĺ
    0.75
     accol
    0.72
     awarded
    0.69
     for
    0.69
    Activations Density 0.256%

    No Known Activations