INDEX

Explanations

questions and phrases that inquire for clarification or further information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 fevere

-0.91

 myſelf

-0.80

 Majefty

-0.80

 crdi

-0.78

 ſever

-0.77

 fubject

-0.76

 ſche

-0.76

 pleaſure

-0.74

ⓧ

-0.72

 pleaf

-0.72

POSITIVE LOGITS

 which

1.05

 Which

1.03

 what

1.02

who

1.00

how

0.99

 whom

0.96

 quais

0.96

 cuales

0.91

Which

0.91

 cual

0.90

Activations Density 0.092%

questions and phrases that inquire for clarification or further information

No Comments

No Known Activations