INDEX

Explanations

proper nouns that indicate organizations or entities issuing statements

oai_token-act-pair · gpt-3.5-turbo

articles and determiners in the text

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

someone

-0.76

anism

-0.74

lords

-0.72

Æ

-0.70

enemy

-0.70

onge

-0.70

effects

-0.70

iev

-0.69

Af

-0.69

enance

-0.67

POSITIVE LOGITS

 scathing

1.06

 slew

1.06

lot

1.05

 plethora

1.04

 lengthy

1.04

 handful

0.99

 whopping

0.98

 flurry

0.97

 preliminary

0.96

 bunch

0.96

Activations Density 0.289%

proper nouns that indicate organizations or entities issuing statements

articles and determiners in the text

No Comments

No Known Activations