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. 15699
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs referring to actions or decisions taken by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong opinions or critiques related to societal issues

    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
    venge
    -0.71
     Colony
    -0.70
    agara
    -0.66
    activate
    -0.66
    ipal
    -0.66
    gor
    -0.66
    ui
    -0.65
    VERTISEMENT
    -0.65
    berra
    -0.64
    processing
    -0.63
    POSITIVE LOGITS
     disingen
    1.05
     plagiar
    1.04
     mislead
    0.99
     rhet
    0.96
     misrepresent
    0.94
     authored
    0.93
     obfusc
    0.93
     promulg
    0.92
     rightly
    0.91
     debunk
    0.88
    Activations Density 0.770%

    No Known Activations