© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1882
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to various actions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to collective behaviors and beliefs among groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itary
    -0.71
     Za
    -0.70
     Ribbon
    -0.63
    ãĥĺ
    -0.61
     Showdown
    -0.61
     Adin
    -0.60
     Frontier
    -0.60
     Late
    -0.59
     licens
    -0.58
     Reborn
    -0.58
    POSITIVE LOGITS
     perceive
    1.29
     think
    1.23
     disbel
    1.13
     empath
    1.13
     believe
    1.13
     understand
    1.11
     adore
    1.08
     distrust
    1.07
     resent
    1.07
     thinks
    1.06
    Activations Density 0.522%

    No Known Activations