INDEX

Explanations

phrases related to stopping or terminating actions

oai_token-act-pair · gpt-3.5-turbo

phrases that involve actions related to pulling or removing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

nown

-0.84

nces

-0.84

arcity

-0.78

hedon

-0.73

anwhile

-0.72

llah

-0.71

chance

-0.71

orld

-0.68

acre

-0.68

urdue

-0.68

POSITIVE LOGITS

 levers

1.03

 punches

0.99

 wagon

0.89

 stool

0.87

 drawer

0.85

 strings

0.84

 curtain

0.81

 conclusions

0.79

 trigger

0.79

 carts

0.78

Activations Density 0.109%

phrases related to stopping or terminating actions

phrases that involve actions related to pulling or removing something

No Comments

No Known Activations