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. 7-RES-JB
    6. 17130
    Prev
    Next
    INDEX
    Explanations

    names or terms related to sports or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.87
    ĸļ
    -0.83
    ACTED
    -0.71
     scrut
    -0.70
    ĪĴ
    -0.69
     enactment
    -0.68
     exception
    -0.65
     rupture
    -0.61
     caucuses
    -0.58
     consistency
    -0.58
    POSITIVE LOGITS
    ierrez
    0.97
    raltar
    0.91
    onz
    0.89
    ppe
    0.88
    anan
    0.87
    veland
    0.87
    apons
    0.86
    apon
    0.85
    reau
    0.85
    estone
    0.85
    Activations Density 0.105%

    No Known Activations