INDEX

Explanations

adjectives describing something beneficial or needed

oai_token-act-pair · gpt-3.5-turbo

references to practicality and utility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Fever

-0.71

olina

-0.67

buck

-0.67

uph

-0.67

opers

-0.65

jong

-0.65

Bom

-0.64

BU

-0.63

eree

-0.62

bitious

-0.61

POSITIVE LOGITS

 idiots

0.95

fully

0.82

 guiActiveUn

0.81

 insights

0.79

tips

0.78

 tools

0.78

tip

0.75

glers

0.74

 useful

0.74

 guiIcon

0.71

Activations Density 0.039%

adjectives describing something beneficial or needed

references to practicality and utility

No Comments

No Known Activations