INDEX

Explanations

patterns related to line breaks and whitespace in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.56

-0.55

";

-0.54

-0.52

-0.51

-0.49

POSITIVE LOGITS

 myſelf

1.06

 Majefty

0.97

 itſelf

0.94

 raiſ

0.94

Efq

0.92

extAlignment

0.92

MethodManager

0.92

 pleaſure

0.90

 purpoſe

0.90

 preſent

0.89

Activations Density 0.220%

patterns related to line breaks and whitespace in text

No Comments

No Known Activations