INDEX

Explanations

the word "there" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "there."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ONSORED

-0.60

IPM

-0.60

 unlaw

-0.57

soever

-0.57

 Warden

-0.56

Reply

-0.56

telling

-0.55

HAHAHAHA

-0.55

Ctrl

-0.53

 miscarriage

-0.53

POSITIVE LOGITS

are

1.16

're

1.03

 aren

1.02

's

1.01

 were

0.99

 exists

0.91

ARE

0.91

 exist

0.90

've

0.90

abouts

0.86

Activations Density 0.101%

the word "there" in various contexts

occurrences of the word "there."

No Comments

No Known Activations