INDEX

Explanations

mentions of successful achievements or accomplishments

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verbs "make" and "made."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

heter

-0.64

æ©Ł

-0.64

 Niet

-0.61

 WATCHED

-0.61

hood

-0.61

Fram

-0.60

bour

-0.58

 interpreted

-0.57

 thinking

-0.57

 begs

-0.57

POSITIVE LOGITS

 landfall

1.17

 strides

1.12

hift

1.11

 headlines

1.00

 appearances

0.91

 waves

0.85

emort

0.80

 cameo

0.78

 playoffs

0.73

 history

0.72

Activations Density 0.111%

mentions of successful achievements or accomplishments

occurrences of the verbs "make" and "made."

No Comments

No Known Activations