INDEX

Explanations

medical or health-related terms and conditions

oai_token-act-pair · gpt-3.5-turbo

the term "ital" in various contexts, likely relating to medical or biological discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bell

-0.72

ModLoader

-0.71

olkien

-0.70

é¾

-0.70

Handle

-0.69

ELL

-0.69

hner

-0.68

EEK

-0.68

UTH

-0.67

ullivan

-0.67

POSITIVE LOGITS

ization

0.95

isation

0.89

ity

0.89

ized

0.87

isations

0.85

ital

0.84

ities

0.84

ITY

0.80

lav

0.80

izations

0.80

Activations Density 0.016%

medical or health-related terms and conditions

the term "ital" in various contexts, likely relating to medical or biological discussions

No Comments

No Known Activations