INDEX

Explanations

keywords related to a specific brand or product, possibly related to technology or media based on the context

oai_token-act-pair · gpt-3.5-turbo

the character 'K' in capital form

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Zionist

-0.69

sov

-0.67

 citiz

-0.66

 Traff

-0.65

 Israelis

-0.64

 Jihad

-0.64

owicz

-0.63

 Fiction

-0.62

stocks

-0.61

 damned

-0.61

POSITIVE LOGITS

ipher

0.73

idia

0.71

pi

0.70

idi

0.70

rete

0.69

anes

0.66

pan

0.64

Profile

0.64

Season

0.63

ETA

0.63

Activations Density 0.000%

keywords related to a specific brand or product, possibly related to technology or media based on the context

the character 'K' in capital form

No Comments

No Known Activations