Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4-RES-JB
    6. 10686
    Prev
    Next
    INDEX
    Explanations

    words related to a specific event or topic, possibly related to a company or project named "Horizon"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Horizon" in various contexts

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

    No Comments

    Negative Logits
    anguage
    -1.09
    conservancy
    -0.82
    ¥µ
    -0.80
    ¬¼
    -0.76
    yles
    -0.76
    oths
    -0.72
    umbnail
    -0.72
    ographically
    -0.71
    NetMessage
    -0.71
    onia
    -0.69
    POSITIVE LOGITS
     Horizon
    1.09
     Collider
    0.91
    vernment
    0.84
     Zero
    0.83
    izons
    0.81
     Petroleum
    0.74
     Cluster
    0.73
     absor
    0.70
    lab
    0.69
    LAB
    0.68
    Activations Density 0.018%

    No Known Activations