INDEX

Explanations

proper nouns from various contexts

oai_token-act-pair · gpt-3.5-turbo

examples of situations or entities that act as representations of broader concepts or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

pora

-0.73

phal

-0.69

BSD

-0.67

Wan

-0.65

 Immunity

-0.65

 holiest

-0.65

Ward

-0.64

 oats

-0.63

AMA

-0.63

 hump

-0.62

POSITIVE LOGITS

ified

1.20

orer

1.16

ifier

1.09

ifies

1.08

ifying

1.03

ifiers

1.03

ification

1.03

ars

0.96

iment

0.93

eness

0.91

Activations Density 0.019%

proper nouns from various contexts

examples of situations or entities that act as representations of broader concepts or themes

No Comments

No Known Activations