INDEX

Explanations

phrases that involve starting or transitioning to something new or different

oai_token-act-pair · gpt-3.5-turbo

phrases indicating expansion or development

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

Gw

-0.68

usercontent

-0.66

utch

-0.65

iewicz

-0.61

pell

-0.60

Mug

-0.60

 yuan

-0.60

ouri

-0.59

rolet

-0.58

cash

-0.58

POSITIVE LOGITS

 secondly

1.15

 thereafter

0.98

 followed

0.98

 gradually

0.94

Secondly

0.93

Phase

0.88

 Secondly

0.82

 progressed

0.78

 progressively

0.77

 foremost

0.77

Activations Density 0.452%

phrases that involve starting or transitioning to something new or different

phrases indicating expansion or development

No Comments

No Known Activations