INDEX

Explanations

sections of text that contain internal citations or quotation marks, indicating referenced or quoted material

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 mean

-0.65

means

-0.64

 means

-0.62

 berarti

-0.58

 MEAN

-0.57

 Means

-0.57

 meaning

-0.56

meaning

-0.54

Means

-0.54

_))

-0.50

POSITIVE LOGITS

 parentheses

1.16

 brackets

1.08

 quotation

1.08

 parenthesis

1.04

 quotations

1.00

 quotes

0.92

 Quote

0.84

quote

0.82

 quoting

0.80

brackets

0.80

Activations Density 0.423%

sections of text that contain internal citations or quotation marks, indicating referenced or quoted material

No Comments

No Known Activations