INDEX

Explanations

phrases indicating strong opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

assertions of existence or presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

uum

-0.69

ative

-0.62

iates

-0.59

ricular

-0.58

 Discuss

-0.57

ples

-0.57

eks

-0.56

ulent

-0.56

 violates

-0.55

 bothers

-0.55

POSITIVE LOGITS

 undoubtedly

1.08

 indeed

1.04

 actually

0.99

 ALWAYS

0.97

 probably

0.94

 yours

0.93

 always

0.90

 usually

0.88

 still

0.87

 invariably

0.87

Activations Density 0.253%

phrases indicating strong opinions or beliefs

assertions of existence or presence

No Comments

No Known Activations