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. 4-RES-JB
    6. 8858
    Prev
    Next
    INDEX
    Explanations

    terms related to advocacy or support for specific social or political causes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advocacy and topics of debate

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

    No Comments

    Negative Logits
     Hath
    -0.94
     Ferguson
    -0.76
     Panther
    -0.74
     palms
    -0.68
     guiActiveUnfocused
    -0.64
    ãģ®éŃĶ
    -0.64
     Faw
    -0.63
     Penn
    -0.63
     messenger
    -0.63
     Gaddafi
    -0.63
    POSITIVE LOGITS
    acy
    1.51
    itive
    1.30
    ates
    1.25
    itives
    1.13
    abulary
    1.11
    acists
    1.09
    acies
    1.02
    alled
    1.02
    acist
    1.00
    ature
    0.98
    Activations Density 0.017%

    No Known Activations