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. 8-RES-JB
    6. 20880
    Prev
    Next
    INDEX
    Explanations

    organizations, names, or entities as well as verbs related to decisions or actions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "has" in various contexts

    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
    icking
    -0.63
    ickle
    -0.61
    eem
    -0.59
     Apart
    -0.58
     wounding
    -0.57
    Northern
    -0.56
     recalls
    -0.55
    ear
    -0.54
    ick
    -0.53
    ealing
    -0.52
    POSITIVE LOGITS
     been
    1.48
    been
    1.23
     gotten
    1.14
    bara
    1.11
     begun
    1.08
     gone
    1.06
     Been
    1.03
     undergone
    1.03
     become
    1.03
     always
    0.96
    Activations Density 0.485%

    No Known Activations