INDEX

Explanations

keywords related to different types of environmental settings or conditions

oai_token-act-pair · gpt-3.5-turbo

references to challenging or complex environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãĥį

-0.74

talk

-0.68

Reply

-0.66

Reuters

-0.65

×ŀ

-0.65

×¨

-0.65

×Ķ

-0.63

\\\\\\\\

-0.61

Delete

-0.61

 vengeance

-0.61

POSITIVE LOGITS

paces

1.02

chool

0.95

ynthesis

0.95

cale

0.93

cape

0.92

uits

0.91

pace

0.90

afety

0.88

hots

0.87

olutions

0.87

Activations Density 0.116%

keywords related to different types of environmental settings or conditions

references to challenging or complex environments

No Comments

No Known Activations