© 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. 8-RES-JB
    11. 7613
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculations or rumors

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols frequently associated with text formatting or encoding issues

    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
     photoc
    -0.68
     swept
    -0.68
     divers
    -0.65
     interf
    -0.64
     fortun
    -0.64
    ifications
    -0.63
     polyg
    -0.62
     dissemin
    -0.62
     comprom
    -0.62
     scatter
    -0.61
    POSITIVE LOGITS
    ¬
    1.06
    ¤
    0.98
    ı
    0.94
    Ļ
    0.93
    ½
    0.92
    ¼
    0.88
    ´
    0.87
    ¿
    0.86
    ¾
    0.85
    Ń
    0.85
    Activations Density 0.232%

    No Known Activations