INDEX

Explanations

buttons or button-related words

oai_token-act-pair · gpt-3.5-turbo

mentions of "buttons" and related user interface elements

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

ctuary

-0.85

ILY

-0.69

nces

-0.69

namese

-0.69

ateur

-0.67

 Profit

-0.66

 Folk

-0.65

 Atmosp

-0.64

 Continuing

-0.63

yon

-0.62

POSITIVE LOGITS

holes

1.05

hole

1.01

button

0.92

btn

0.87

pus

0.87

bell

0.87

nuts

0.85

 button

0.85

 buttons

0.81

 clicked

0.80

Activations Density 0.036%

buttons or button-related words

mentions of "buttons" and related user interface elements

No Comments

No Known Activations