INDEX

Explanations

email-related content

oai_token-act-pair · gpt-3.5-turbo

incidents of invalid interactions or responses, often related to subscription errors or interruptions

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

ichick

-0.72

orer

-0.67

qs

-0.67

bd

-0.65

breakers

-0.63

opt

-0.61

draft

-0.61

kl

-0.61

Ó

-0.61

ãĥ¼ãĥĨãĤ£

-0.61

POSITIVE LOGITS

 IMAGES

0.82

PORT

0.73

BBC

0.73

LOS

0.69

GREEN

0.67

*/(

0.67

LAB

0.66

Warning

0.63

 presenter

0.62

 guid

0.62

Activations Density 0.071%

email-related content

incidents of invalid interactions or responses, often related to subscription errors or interruptions

No Comments

No Known Activations