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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 9854
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and activism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of outrage and discussions around rights and freedoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.75
    ocamp
    -0.71
     Chocobo
    -0.63
     Presumably
    -0.59
     âĵĺ
    -0.59
    arthed
    -0.58
    dq
    -0.58
    CG
    -0.56
     Pwr
    -0.55
     Hilbert
    -0.55
    POSITIVE LOGITS
     injust
    1.15
     injustice
    1.07
     disrespect
    1.06
     disgrace
    1.00
     oppressed
    0.98
     bigotry
    0.96
     hateful
    0.96
     despicable
    0.96
     oppress
    0.94
     barbaric
    0.91
    Activations Density 1.094%

    No Known Activations