INDEX

Explanations

the word "kins"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "kins"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ntil

-0.69

ħĭ

-0.69

 duplication

-0.68

AQ

-0.62

senal

-0.62

iners

-0.61

 reinforcement

-0.61

ãĥ¼ãĥ³

-0.61

ccording

-0.60

 simultane

-0.59

POSITIVE LOGITS

kins

1.28

kie

1.16

hip

1.10

kin

1.05

hips

1.02

haw

1.01

creen

0.96

sey

0.96

cence

0.96

ley

0.95

Activations Density 0.010%

the word "kins"

occurrences of the word "kins"

No Comments

No Known Activations