INDEX

Explanations

instances of the word "guess"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "guess" indicating speculation or uncertainty

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

rome

-0.70

cler

-0.68

 Antar

-0.67

vis

-0.67

waters

-0.67

roma

-0.65

Js

-0.65

andals

-0.64

Uncommon

-0.64

pling

-0.64

POSITIVE LOGITS

 guess

1.49

 guesses

1.32

 guessing

1.14

 Guess

1.13

 guessed

0.99

itial

0.87

 interpretation

0.75

 Leilan

0.75

estamp

0.71

 excuse

0.71

Activations Density 0.013%

instances of the word "guess"

instances of the word "guess" indicating speculation or uncertainty

No Known Activations