INDEX

Explanations

mentions of places or locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "de la" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

âĦ¢:

-0.85

lessly

-0.79

locks

-0.79

flies

-0.78

wolves

-0.76

tons

-0.74

LER

-0.74

LESS

-0.73

bucks

-0.73

lers

-0.73

POSITIVE LOGITS

uren

0.93

vel

0.80

 lang

0.77

isse

0.77

 Liga

0.74

Rey

0.70

ction

0.70

 lett

0.70

Ã¯

0.70

Ma

0.67

Activations Density 0.025%

mentions of places or locations

occurrences of the phrase "de la" in various contexts

No Comments

No Known Activations