INDEX

Explanations

words related to personal hygiene and grooming, specifically items like razors, toothpaste, and soap

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals named "Jazmine" or similar variants

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

 Seah

-0.66

 Fargo

-0.64

 foremost

-0.64

 Impossible

-0.64

 Kraken

-0.64

ãĤ©

-0.63

 Kepler

-0.63

 Carolina

-0.61

nces

-0.60

perature

-0.60

POSITIVE LOGITS

ombie

1.10

hou

1.09

hang

0.99

awa

0.93

illion

0.91

quez

0.91

 Sharif

0.91

eez

0.91

ahar

0.90

ahn

0.87

Activations Density 0.020%

words related to personal hygiene and grooming, specifically items like razors, toothpaste, and soap

references to specific individuals named "Jazmine" or similar variants

No Comments

No Known Activations