© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1772
    Prev
    Next
    INDEX
    Explanations

    words related to charging, surcharge, and cost

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial charges and fees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mock
    -0.72
     puppet
    -0.70
     nightmares
    -0.68
     hang
    -0.65
     Sut
    -0.63
     orphan
    -0.63
     ethn
    -0.61
     abstract
    -0.61
     pupp
    -0.59
     Schn
    -0.59
    POSITIVE LOGITS
    charged
    3.69
    charge
    3.66
    charges
    3.39
    charging
    3.34
    charg
    2.63
    Charge
    2.32
    Charg
    1.86
     Charge
    1.64
    Charges
    1.53
     Charg
    1.48
    Activations Density 0.017%

    No Known Activations