INDEX

Explanations

instances of the word "all."

oai_token-act-pair · gpt-3.5-turbo

phrases and concepts that include the word "all" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yip

-0.82

raid

-0.72

full

-0.66

TW

-0.65

edin

-0.65

lav

-0.65

nell

-0.63

itent

-0.62

deck

-0.61

yi

-0.60

POSITIVE LOGITS

usions

1.14

 else

1.14

 sorts

1.13

 manner

1.09

igators

1.08

 kinds

1.07

iances

1.01

usion

0.99

ocating

0.98

uding

0.97

Activations Density 0.076%

instances of the word "all."

phrases and concepts that include the word "all" in various contexts

No Comments

No Known Activations