INDEX

Explanations

words related to authority figures or positions of power

oai_token-act-pair · gpt-3.5-turbo

references to the article "the" in various contexts

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

SPONSORED

-0.88

VICE

-0.72

wine

-0.68

heses

-0.67

Course

-0.67

JUST

-0.66

 SetFontSize

-0.66

pps

-0.66

estyles

-0.65

owned

-0.64

POSITIVE LOGITS

 proverbial

0.92

 notion

0.87

 edges

0.83

 weeds

0.83

 heels

0.83

rug

0.83

 unsuspecting

0.82

 slightest

0.81

 offending

0.81

 enorm

0.81

Activations Density 0.470%

words related to authority figures or positions of power

references to the article "the" in various contexts

No Comments

No Known Activations