INDEX

Explanations

occurrences of the word "act" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

ValueStyle

-0.84

WithIOException

-0.73

uxxxx

-0.70

ineno

-0.68

MessageTagHelper

-0.67

 صوتيه

-0.67

 ExecuteAsync

-0.66

FunctionFlags

-0.65

MigrationBuilder

-0.64

 HasFactory

-0.63

POSITIVE LOGITS

act

1.30

act

1.20

Act

1.02

Act

1.02

 acts

0.96

 acted

0.90

ACT

0.87

ACT

0.75

 actúa

0.70

acts

0.64

Activations Density 0.245%

occurrences of the word "act" in various contexts

No Comments

No Known Activations