INDEX

Explanations

words related to a specific product or brand

oai_token-act-pair · gpt-3.5-turbo

specific brand names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

mix

-0.89

elli

-0.81

ainer

-0.80

thing

-0.78

long

-0.77

Neal

-0.76

stantial

-0.75

mire

-0.75

thinking

-0.74

ĸļ

-0.74

POSITIVE LOGITS

jriwal

0.78

arettes

0.77

 Beats

0.74

 Immunity

0.72

 sclerosis

0.70

 Emblem

0.67

Grade

0.66

 secondly

0.64

 parachute

0.63

 Amph

0.63

Activations Density 0.000%

words related to a specific product or brand

specific brand names

No Comments

No Known Activations