INDEX

Explanations

instances of the word "riding" and its variations in context

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

 myſelf

-1.16

 raiſ

-1.15

 createState

-1.15

 uſed

-1.11

 anſ

-1.11

ſelf

-1.10

 ſte

-1.08

ſelves

-1.06

 Anſ

-1.05

 ſche

-1.04

POSITIVE LOGITS

void

0.79

0.71

 void

0.69

int

0.63

 rode

0.61

 boolean

0.61

0.59

boolean

0.59

↵↵

0.59

Activations Density 0.221%

instances of the word "riding" and its variations in context

No Comments

No Known Activations