INDEX

Explanations

names related to individuals

oai_token-act-pair · gpt-3.5-turbo

the repetition of the substring "lo"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

manship

-0.77

chell

-0.73

 tremend

-0.71

ãĥĩ

-0.71

 eleph

-0.68

imental

-0.67

 Democr

-0.66

âĶģ

-0.64

glass

-0.64

icles

-0.64

POSITIVE LOGITS

fty

1.15

zzi

1.10

zzle

1.09

ppy

1.07

pper

1.06

ven

1.03

veland

0.94

pped

0.94

ights

0.93

oyd

0.91

Activations Density 0.012%

names related to individuals

the repetition of the substring "lo"

No Comments

No Known Activations