INDEX

Explanations

names of various locations

oai_token-act-pair · gpt-3.5-turbo

elements related to data science and programming concepts

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

çĶ°

-0.85

theless

-0.71

NB

-0.71

 secondly

-0.69

 indo

-0.68

çľ

-0.68

 Southern

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.67

PB

-0.67

ãĥīãĥ©ãĤ´ãĥ³

-0.66

POSITIVE LOGITS

icker

1.07

ig

1.02

ight

1.01

ock

1.00

itt

0.98

ocker

0.95

ear

0.94

igs

0.94

aint

0.93

iser

0.92

Activations Density 0.310%

names of various locations

elements related to data science and programming concepts

No Comments

No Known Activations