INDEX

Explanations

political and news-related terms and entities

oai_token-act-pair · gpt-3.5-turbo

references to media and visual elements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soType

-0.77

DERR

-0.77

fired

-0.73

soDeliveryDate

-0.70

ocr

-0.67

mingham

-0.64

edited

-0.62

tested

-0.62

ample

-0.62

 stated

-0.61

POSITIVE LOGITS

]'

0.76

 Photos

0.73

 Signs

0.71

aval

0.69

 Mysterious

0.68

htaking

0.68

:'

0.68

 Deadly

0.65

 resil

0.65

Photos

0.64

Activations Density 0.068%

political and news-related terms and entities

references to media and visual elements

No Comments

No Known Activations