© 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. 2-RES-JB
    11. 12312
    Prev
    Next
    INDEX
    Explanations

    mentions of authorities in news or official contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to authorities and their actions or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Humanity
    -0.74
    ces
    -0.72
    Posts
    -0.71
    CONT
    -0.71
    READ
    -0.67
    leaf
    -0.67
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    OUT
    -0.65
     Brave
    -0.64
    vious
    -0.64
    POSITIVE LOGITS
     authorities
    1.21
     Authorities
    0.97
     officials
    0.90
     confir
    0.90
     regulators
    0.85
     estab
    0.84
    emetery
    0.84
     agencies
    0.83
     authorized
    0.80
     regulator
    0.78
    Activations Density 0.021%

    No Known Activations