INDEX

Explanations

phrases related to specific locations or entities within a broader context

oai_token-act-pair · gpt-3.5-turbo

phrases indicating urban settings or city-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Checking

-0.67

 Additional

-0.62

 Scotia

-0.62

 corresponding

-0.61

 Solution

-0.60

iHUD

-0.58

phrine

-0.57

 Muller

-0.56

 Drivers

-0.56

abin

-0.56

POSITIVE LOGITS

 ostensibly

0.98

 frankly

0.97

 desperately

0.95

 arguably

0.94

 admittedly

0.93

 seemingly

0.92

 sorely

0.92

 barely

0.92

 notoriously

0.90

 hardly

0.88

Activations Density 0.276%

phrases related to specific locations or entities within a broader context

phrases indicating urban settings or city-related contexts

No Comments

No Known Activations