INDEX

Explanations

names or entities with unusual capitalization patterns

oai_token-act-pair · gpt-3.5-turbo

instances of proper nouns or names

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

SPONSORED

-0.92

 ..."

-0.69

 thereof

-0.67

 respectively

-0.67

=]

-0.65

 steroids

-0.62

 guiIcon

-0.62

mov

-0.60

LIST

-0.60

NUM

-0.60

POSITIVE LOGITS

 Profile

0.88

utsu

0.77

ayan

0.76

abad

0.76

obia

0.74

oni

0.74

 meanwhile

0.74

yn

0.73

iasis

0.73

inho

0.72

Activations Density 0.359%

names or entities with unusual capitalization patterns

instances of proper nouns or names

No Comments

No Known Activations