INDEX

Explanations

phrases related to locations or entities starting with the letter 'E'

oai_token-act-pair · gpt-3.5-turbo

references to the letter "E" and its various contexts

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

 Rebels

-0.82

 following

-0.73

 Blizz

-0.71

 heads

-0.68

 tackling

-0.67

 enclosed

-0.66

 bitters

-0.66

 timing

-0.66

 descending

-0.65

 juggling

-0.65

POSITIVE LOGITS

CA

1.19

MW

1.15

aren

1.14

NA

1.13

DP

1.13

CC

1.12

SW

1.11

VA

1.10

NN

1.10

CS

1.09

Activations Density 0.221%

phrases related to locations or entities starting with the letter 'E'

references to the letter "E" and its various contexts

No Comments

No Known Activations