INDEX

Explanations

short passages at the end of 'To Continue reading the main story' advertisements

oai_token-act-pair · gpt-3.5-turbo

sections of text that indicate content or textual structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

asel

-0.67

addin

-0.64

uthor

-0.64

 unsuspecting

-0.63

cius

-0.61

 barg

-0.61

 Stellar

-0.61

apon

-0.60

adelphia

-0.60

cipled

-0.58

POSITIVE LOGITS

Companies

0.79

JUST

0.75

Incre

0.74

Bloomberg

0.74

Likewise

0.73

Certain

0.73

Similar

0.71

Mi

0.71

Contribut

0.71

Files

0.71

Activations Density 0.019%

short passages at the end of 'To Continue reading the main story' advertisements

sections of text that indicate content or textual structure

No Comments

No Known Activations