INDEX

Explanations

phrases or words related to creating a noticeable impact or change

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "dent."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

MQ

-0.75

Recommend

-0.73

Grey

-0.73

 Gathering

-0.73

 Gemini

-0.70

Supp

-0.70

Mae

-0.70

GREEN

-0.67

HCR

-0.67

çĦ

-0.66

POSITIVE LOGITS

 dent

1.41

istry

1.25

icer

0.91

icles

0.89

ricular

0.85

icle

0.84

 braces

0.83

icular

0.82

rition

0.81

 Dent

0.81

Activations Density 0.003%

phrases or words related to creating a noticeable impact or change

repeated mentions of the word "dent."

No Comments

No Known Activations