INDEX

Explanations

phrases introducing lists of items or information

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate examples or lists

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

culosis

-0.77

iosity

-0.74

etheless

-0.73

isma

-0.72

 affair

-0.72

dom

-0.71

amphetamine

-0.69

akery

-0.68

rouse

-0.67

jp

-0.65

POSITIVE LOGITS

 examples

0.90

 links

0.86

 excerpts

0.84

 screenshots

0.84

 pointers

0.78

 some

0.73

 quotes

0.73

:(

0.73

 snapshots

0.73

 suggestions

0.73

Activations Density 0.022%

phrases introducing lists of items or information

phrases that indicate examples or lists

No Comments

No Known Activations