INDEX

Explanations

warnings about safety or caution related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 FetchType

-0.69

konomi

-0.67

 مرئيه

-0.65

ksesta

-0.65

lodash

-0.65

 Exactos

-0.63

tvguidetime

-0.60

Subviews

-0.60

iecie

-0.60

GETHER

-0.59

POSITIVE LOGITS

 warning

3.36

 Warning

3.08

 warnings

3.06

 warn

3.03

Warning

2.81

warning

2.80

 Warnings

2.76

 warned

2.75

 WARNING

2.70

 warns

2.69

Activations Density 0.046%

warnings about safety or caution related to various contexts

No Comments

No Known Activations