INDEX

Explanations

phrases related to physical actions and locations

oai_token-act-pair · gpt-3.5-turbo

elements related to storytelling and narrative progression

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

âĦ¢:

-0.73

osponsors

-0.72

 âĢº

-0.67

osphere

-0.64

 domestically

-0.60

ËĪ

-0.59

 billionaires

-0.59

 Silicon

-0.58

 Historically

-0.58

oliberal

-0.57

POSITIVE LOGITS

 hurried

0.81

gered

0.77

 yelled

0.76

 panicked

0.75

Eventually

0.73

upon

0.71

 proceeded

0.71

Suddenly

0.70

Later

0.70

 calmed

0.69

Activations Density 1.501%

phrases related to physical actions and locations

elements related to storytelling and narrative progression

No Comments

No Known Activations