INDEX

Explanations

food-related words

oai_token-act-pair · gpt-3.5-turbo

specific nouns related to sensory experiences and events

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

.).

-0.81

.<

-0.78

NetMessage

-0.75

%.

-0.73

>.

-0.69

BuyableInstoreAndOnline

-0.67

''.

-0.65

srf

-0.65

.ãĢį

-0.64

$.

-0.64

POSITIVE LOGITS

 goes

0.80

 enters

0.73

 arrived

0.73

 came

0.73

 recovers

0.71

 disappears

0.71

 grows

0.71

 evolves

0.70

 differs

0.70

 arrives

0.69

Activations Density 0.784%

food-related words

specific nouns related to sensory experiences and events

No Comments

No Known Activations