INDEX

Explanations

mentions of media content such as pictures and analysis

oai_token-act-pair · gpt-3.5-turbo

words and phrases associated with various types of media and reporting

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

chest

-0.70

gie

-0.65

paying

-0.64

$.

-0.64

lug

-0.63

TIT

-0.61

 grounding

-0.59

Moz

-0.57

 Grac

-0.56

POSITIVE LOGITS

 ensued

0.80

ccording

0.73

surprisingly

0.72

 spokesman

0.70

ioned

0.68

ogether

0.67

 confirms

0.66

 indicates

0.65

 analyst

0.64

nown

0.63

Activations Density 0.298%

mentions of media content such as pictures and analysis

words and phrases associated with various types of media and reporting

No Comments

No Known Activations