INDEX

Explanations

images or descriptions related to a specific location or position - "in front"

oai_token-act-pair · gpt-3.5-turbo

mentions of being "in front of" something or someone

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

IRO

-0.79

Rating

-0.74

cci

-0.72

======

-0.65

gger

-0.64

zn

-0.64

tar

-0.63

hell

-0.63

ggle

-0.63

fortune

-0.63

POSITIVE LOGITS

row

0.79

mast

0.74

 lawn

0.70

shore

0.68

eering

0.68

office

0.67

front

0.67

 Tanz

0.65

sight

0.65

stadt

0.65

Activations Density 0.012%

images or descriptions related to a specific location or position - "in front"

mentions of being "in front of" something or someone

No Comments

No Known Activations