INDEX

Explanations

references to icons 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

+#+#

-0.57

RuleContext

-0.53

 escrit

-0.53

xmlWriter

-0.53

 FormBuilder

-0.53

σκε

-0.51

 siitä

-0.51

dataclass

-0.50

ệc

-0.49

UpInside

-0.49

POSITIVE LOGITS

IP

0.88

 Tony

0.69

 Anthony

0.68

Rüyada

0.67

IPs

0.66

 icons

0.65

 onAnimation

0.65

 Icons

0.65

Tony

0.64

transform

0.64

Activations Density 0.067%

references to icons in various contexts

No Comments

No Known Activations