INDEX

Explanations

mentions of the word "ride" with varying activations, suggesting a focus on activities or experiences involving riding or the concept of riding

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.61

 nakalista

-0.52

ItemLayout

-0.49

 CreateTagHelper

-0.49

 Szen

-0.49

\{\\

-0.47

 Polen

-0.47

TextHelper

-0.47

 חיצוניים

-0.47

mientos

-0.46

POSITIVE LOGITS

 ride

1.37

 Ride

1.23

 rides

1.22

 RIDE

1.21

 riding

1.21

 riders

1.19

 Rides

1.18

 rode

1.16

Ride

1.15

 rider

1.14

Activations Density 0.067%

mentions of the word "ride" with varying activations, suggesting a focus on activities or experiences involving riding or the concept of riding

No Comments

No Known Activations