INDEX

Explanations

phrases indicating actions or events that occurred before a specific point in time

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Prior" followed by a number indicating a sequence or timeline of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

aden

-0.83

 darts

-0.65

Ã¼r

-0.65

asp

-0.62

tower

-0.61

RO

-0.61

 Pistons

-0.61

immer

-0.60

RF

-0.60

umbling

-0.59

POSITIVE LOGITS

itized

1.06

ities

1.05

itiz

0.94

icip

0.86

IOR

0.86

 Prior

0.81

requisite

0.80

alities

0.80

requisites

0.77

Prior

0.76

Activations Density 0.005%

phrases indicating actions or events that occurred before a specific point in time

occurrences of the word "Prior" followed by a number indicating a sequence or timeline of events

No Comments

No Known Activations