INDEX

Explanations

references to a specific author or theorist

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RenderAtEndOf

-1.05

 оригіналу

-0.90

Rüyada

-0.84

MigrationBuilder

-0.83

Hochspringen

-0.76

InputBorder

-0.75

GraphicsUnit

-0.75

 članak

-0.75

StoryboardSegue

-0.75

#+#

-0.74

POSITIVE LOGITS

Ste

1.06

ste

1.05

Ste

0.97

ste

0.96

te

0.82

STE

0.73

 stepped

0.72

 steamed

0.66

STEP

0.65

 STEP

0.63

Activations Density 0.073%

references to a specific author or theorist

No Comments

No Known Activations