INDEX

Explanations

mentions or titles that start with the letter "K."

oai_token-act-pair · gpt-3.5-turbo

unique end-of-text markers or formatting indicators

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.70

 expires

-0.66

 diapers

-0.64

zona

-0.61

Ø©

-0.60

ÙĴ

-0.60

 heartbeat

-0.60

TTL

-0.60

cipl

-0.59

ãĥ¼ãĥĨãĤ£

-0.59

POSITIVE LOGITS

EEP

1.10

orea

1.09

laus

1.08

irk

1.07

essel

1.06

rieg

1.05

ISS

1.03

ernel

1.02

eeper

1.02

won

1.01

Activations Density 0.032%

mentions or titles that start with the letter "K."

unique end-of-text markers or formatting indicators

No Comments

No Known Activations