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. 8-RES-JB
    6. 17498
    Prev
    Next
    INDEX
    Explanations

    specific instances where an entity states its actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" followed by auxiliary verbs indicating various states or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charisma
    -0.70
     Conquest
    -0.68
     trivia
    -0.64
     vanity
    -0.61
    stead
    -0.60
     TED
    -0.60
    200000
    -0.60
     Mens
    -0.60
     Asgard
    -0.60
     Ent
    -0.58
    POSITIVE LOGITS
     regretted
    0.89
     notified
    0.84
     intends
    0.84
    ©¶æ
    0.82
     reached
    0.81
     encount
    0.79
     expects
    0.79
     received
    0.78
     honoured
    0.76
     intend
    0.75
    Activations Density 0.134%

    No Known Activations