INDEX

Explanations

references to thresholds in 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

pyplot

-0.65

\\

-0.64

गा

-0.60

kehrt

-0.59

Stab

-0.59

 vostri

-0.58

 foglal

-0.58

 vestiti

-0.57

ⓧ

-0.56

orsese

-0.56

POSITIVE LOGITS

 threshold

3.09

 Threshold

2.78

threshold

2.74

 thresholds

2.71

Threshold

2.60

THRESHOLD

2.16

thresholds

2.06

reshold

1.91

 seuil

1.90

阈

1.86

Activations Density 0.082%

references to thresholds in various contexts

No Comments

No Known Activations