INDEX

Explanations

references to visual elements or visual representation 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AddTagHelper

-0.63

addGroup

-0.63

antMatchers

-0.62

forKey

-0.61

KEYCODE

-0.60

RuleContext

-0.60

 replying

-0.59

__((

-0.59

ineno

-0.58

 ordini

-0.58

POSITIVE LOGITS

 visual

3.42

 Visual

3.21

visual

3.12

Visual

3.09

 VISUAL

2.91

VISUAL

2.79

 visuals

2.50

 visuel

2.32

 visually

2.25

 visuelle

2.20

Activations Density 0.073%

references to visual elements or visual representation in text

No Comments

No Known Activations