INDEX

Explanations

locations or places mentioned in sentences

oai_token-act-pair · gpt-3.5-turbo

terms related to searching or seeking in various contexts, such as jobs, relationships, and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eatures

-0.73

 deliberations

-0.65

ãĥ¼ãĤ¯

-0.63

 ACTIONS

-0.63

elvet

-0.61

ãĥĭ

-0.60

inion

-0.58

imation

-0.58

irements

-0.58

Pry

-0.58

POSITIVE LOGITS

 suitable

1.14

 elusive

1.07

 willing

1.05

 trustworthy

1.03

 worthy

1.02

 somewhere

0.90

 elsewhere

0.90

 acceptable

0.88

atable

0.88

 lurking

0.85

Activations Density 0.270%

locations or places mentioned in sentences

terms related to searching or seeking in various contexts, such as jobs, relationships, and locations

No Comments

No Known Activations