INDEX

Explanations

lists enumerating items or suggestions

oai_token-act-pair · gpt-3.5-turbo

lists or recommendations of items or tips

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

ĸļ

-0.96

ylum

-0.77

ivism

-0.77

IVER

-0.73

ariat

-0.70

anship

-0.69

iosis

-0.69

adra

-0.67

externalActionCode

-0.67

iries

-0.67

POSITIVE LOGITS

 quotes

0.95

 examples

0.95

 testim

0.93

 positives

0.87

 highlights

0.82

 recommendations

0.80

 celebrities

0.80

 excerpts

0.79

 acron

0.77

 items

0.77

Activations Density 0.232%

lists enumerating items or suggestions

lists or recommendations of items or tips

No Comments

No Known Activations