INDEX

Explanations

adjectives and adverbs indicating predominance or focus

oai_token-act-pair · gpt-3.5-turbo

frequency qualifiers indicating generalization or predominance in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

anth

-0.78

uers

-0.75

ophys

-0.68

Reviewer

-0.67

ylan

-0.65

 somehow

-0.64

emption

-0.63

hani

-0.63

Moreover

-0.62

orf

-0.61

POSITIVE LOGITS

tenance

0.85

 consisting

0.84

 concerned

0.82

 consisted

0.81

 consist

0.79

 consists

0.77

 aimed

0.74

foc

0.73

 comprised

0.73

 focused

0.71

Activations Density 0.063%

adjectives and adverbs indicating predominance or focus

frequency qualifiers indicating generalization or predominance in statements

No Comments

No Known Activations