INDEX

Explanations

phrases related to specific geographical locations

oai_token-act-pair · gpt-3.5-turbo

mentions of "Mountain" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ional

-0.99

orate

-0.90

ifice

-0.89

metic

-0.86

Â·Â·

-0.81

ded

-0.78

lest

-0.78

ivity

-0.76

ions

-0.75

ifiable

-0.75

POSITIVE LOGITS

 Mountain

0.89

 Bike

0.84

 Island

0.84

 biking

0.82

 Riders

0.82

 Alto

0.79

 footh

0.79

 Valley

0.78

 Sinai

0.77

lake

0.77

Activations Density 0.012%

phrases related to specific geographical locations

mentions of "Mountain" in various contexts

No Comments

No Known Activations