INDEX

Explanations

the word "That" at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

statements that begin with "That," indicating a focus on declarative claims or assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thro

-0.72

"],"

-0.69

hips

-0.68

natureconservancy

-0.66

perse

-0.65

boards

-0.64

vre

-0.63

cycles

-0.63

emis

-0.63

este

-0.62

POSITIVE LOGITS

cher

0.87

 culminated

0.85

 mattered

0.83

 same

0.82

 includes

0.80

 translates

0.79

 sounds

0.78

 pesky

0.77

 begs

0.75

 sounded

0.74

Activations Density 0.126%

the word "That" at the beginning of sentences

statements that begin with "That," indicating a focus on declarative claims or assertions

No Comments

No Known Activations