INDEX

Explanations

terms related to specific locations or events like cities, dog breeds, and movie titles

oai_token-act-pair · gpt-3.5-turbo

references to specific locations and events

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

".[

-1.03

."[

-0.94

SPONSORED

-0.82

 Logged

-0.79

":[

-0.78

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.78

)."

-0.77

"],"

-0.76

"},"

-0.76

:[

-0.75

POSITIVE LOGITS

 underrated

0.81

 formerly

0.64

ensibly

0.62

enic

0.61

eworld

0.59

 classy

0.59

ounty

0.58

 award

0.58

eaturing

0.57

erenn

0.57

Activations Density 1.039%

terms related to specific locations or events like cities, dog breeds, and movie titles

references to specific locations and events

No Comments

No Known Activations