INDEX

Explanations

phrases that contain the word "Media"

oai_token-act-pair · gpt-3.5-turbo

references to media 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

ranch

-0.90

clus

-0.76

İĭ

-0.70

ought

-0.70

Ĥª

-0.68

Phi

-0.67

xxx

-0.66

profits

-0.66

construct

-0.65

ĪĴ

-0.64

POSITIVE LOGITS

 caption

0.97

Media

0.81

 Matters

0.80

 playback

0.78

Buzz

0.71

fax

0.70

Wiki

0.70

 Attribution

0.70

Guard

0.69

 News

0.68

Activations Density 0.006%

phrases that contain the word "Media"

references to media content

No Comments

No Known Activations