INDEX

Explanations

concepts related to thought and introspection

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FilterChain

-0.79

drücken

-0.73

-0.72

ers

-0.71

legungen

-0.71

-0.70

dą

-0.68

er

-0.68

POSITIVE LOGITS

 Thought

1.44

 THOUGHT

1.41

thought

1.38

Thought

1.32

 thought

1.25

thoughts

1.05

 thoughts

1.04

 Thoughts

0.98

SOT

0.93

 pensées

0.87

Activations Density 0.090%

concepts related to thought and introspection

No Comments

No Known Activations