INDEX

Explanations

prompts asking users to click on specific elements or buttons on a webpage

oai_token-act-pair · gpt-3.5-turbo

actions related to clicking buttons or links in digital content

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

ngth

-0.80

lycer

-0.70

ilic

-0.69

ufact

-0.68

angering

-0.67

udeb

-0.66

contained

-0.62

noon

-0.62

ensical

-0.62

church

-0.61

POSITIVE LOGITS

 button

1.12

 buttons

0.96

ĵĺ

0.77

 slider

0.73

 accelerator

0.73

 zoom

0.72

 switches

0.71

 arrow

0.71

tab

0.71

 arrows

0.71

Activations Density 0.087%

prompts asking users to click on specific elements or buttons on a webpage

actions related to clicking buttons or links in digital content

No Comments

No Known Activations