© 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. 11-RES-JB
    11. 877
    Prev
    Next
    INDEX
    Explanations

    references to specific monetary amounts, especially in US dollars

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts represented in dollar signs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behavi
    -0.67
     earliest
    -0.63
     enthusi
    -0.61
     afore
    -0.61
     boun
    -0.60
     Mim
    -0.60
     conflic
    -0.60
     Mesa
    -0.59
     looph
    -0.59
     princ
    -0.58
    POSITIVE LOGITS
    300
    1.66
    1000
    1.66
    100
    1.64
    200
    1.63
    600
    1.61
    400
    1.60
    5000
    1.60
    800
    1.56
    700
    1.55
    150
    1.55
    Activations Density 0.069%

    No Known Activations