INDEX

Explanations

phrases starting with "Given" that imply a premise or condition

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a conditional or causal relationship

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

jer

-0.77

Bay

-0.76

ater

-0.72

oiler

-0.72

alde

-0.71

uttering

-0.71

aird

-0.68

antes

-0.67

OAD

-0.67

imming

-0.66

POSITIVE LOGITS

rely

0.81

©¶æ

0.75

pend

0.73

 schedules

0.69

 circumstances

0.69

imaru

0.68

stellar

0.65

 hindsight

0.65

sid

0.64

 permissions

0.63

Activations Density 0.033%

phrases starting with "Given" that imply a premise or condition

phrases that indicate a conditional or causal relationship

No Comments

No Known Activations