INDEX

Explanations

references to mountain-related entities or activities

oai_token-act-pair · gpt-3.5-turbo

references to mountains

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

BACK

-0.89

âĸ¬

-0.86

 Machina

-0.82

NER

-0.81

lest

-0.79

Federal

-0.78

Dialogue

-0.77

uel

-0.77

âĸ¬âĸ¬

-0.75

encia

-0.74

POSITIVE LOGITS

 biking

1.11

 mountain

1.00

 mountains

0.91

 skiing

0.86

 ridge

0.86

 Everest

0.84

 laure

0.84

 climbers

0.83

 canyon

0.83

 Sinai

0.82

Activations Density 0.018%

references to mountain-related entities or activities

references to mountains

No Comments

No Known Activations