Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17889
    Prev
    Next
    INDEX
    Explanations

    words related to contrasting or opposing concepts

    oai_token-act-pair · gpt-3.5-turbo

    academic terms related to thesis statements and arguments

    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
     customers
    -0.65
     Whit
    -0.64
     daily
    -0.64
     live
    -0.64
    bro
    -0.61
     Libya
    -0.61
     traffic
    -0.60
     Libyan
    -0.60
     gritty
    -0.60
     beans
    -0.59
    POSITIVE LOGITS
    hesis
    4.88
    heses
    3.43
    hetical
    2.45
    hetically
    1.33
    hes
    1.32
    hetics
    1.20
    rait
    1.02
    agonist
    0.98
    inction
    0.98
    hetic
    0.95
    Activations Density 0.027%

    No Known Activations