INDEX

Explanations

phrases introducing biographical information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verb "was" indicating past actions or states

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 entails

-0.67

holders

-0.65

 antioxid

-0.63

ological

-0.63

 Which

-0.62

 Millions

-0.62

Make

-0.61

 IMAGES

-0.60

 HAVE

-0.59

 sexes

-0.59

POSITIVE LOGITS

hes

1.04

 able

1.00

 born

0.97

wolves

0.92

wolf

0.92

nt

0.91

 briefed

0.90

 originally

0.86

 sentenced

0.85

 awarded

0.85

Activations Density 0.388%

phrases introducing biographical information

occurrences of the verb "was" indicating past actions or states

No Comments

No Known Activations