INDEX

Explanations

terms related to environmental contexts and transitions

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

DoubleQuotes

-0.74

TypedDataSet

-0.74

 direta

-0.72

 kaarangay

-0.70

IsMutable

-0.69

 CURIAM

-0.69

ppelin

-0.68

 doInBackground

-0.67

 uska

-0.66

ngths

-0.66

POSITIVE LOGITS

 Environment

1.25

Environment

1.25

 Environ

0.91

 Environmental

0.85

 Event

0.82

 ENVIRONMENT

0.82

EV

0.76

environment

0.73

EV

0.72

Env

0.72

Activations Density 0.237%

terms related to environmental contexts and transitions

No Comments

No Known Activations