INDEX

Explanations

words related to universities or educational institutions

oai_token-act-pair · gpt-3.5-turbo

occurrences or references to the letter "e"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.79

lime

-0.77

iets

-0.71

NESS

-0.69

DOWN

-0.68

irtual

-0.67

anova

-0.66

 BaseType

-0.66

iator

-0.66

 sidx

-0.66

POSITIVE LOGITS

lements

1.26

cki

1.13

gger

1.06

gypt

1.06

zza

1.05

astern

1.03

agles

1.02

agle

1.01

ld

1.00

ck

1.00

Activations Density 0.050%

words related to universities or educational institutions

occurrences or references to the letter "e"

No Comments

No Known Activations