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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17651
    Prev
    Next
    INDEX
    Explanations

    words related to violent actions or tools

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or verbs presented in a 'ed' form

    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
     modification
    -0.80
    oller
    -0.72
     escalation
    -0.72
     blaze
    -0.70
     Schumer
    -0.69
     Daniels
    -0.66
     Dickinson
    -0.66
     Scotia
    -0.66
     flick
    -0.66
     Wiz
    -0.66
    POSITIVE LOGITS
    paren
    1.17
    earth
    1.04
    bodied
    1.03
    by
    1.03
    upon
    1.01
    enough
    1.00
    looking
    1.00
    fee
    0.99
    dead
    0.98
    through
    0.96
    Activations Density 0.043%

    No Known Activations