INDEX

Explanations

occurrences of the word "gee" or variations like "gees" and "Geeves"

oai_token-act-pair · gpt-3.5-turbo

words containing variations of the suffix "ee", particularly in names or titles

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

ãĥķãĤ©

-0.97

iques

-0.75

ãĤ¤ãĥĪ

-0.75

iferation

-0.72

 tremend

-0.70

 traff

-0.68

ifiable

-0.68

acity

-0.66

ĸļ

-0.66

ainer

-0.64

POSITIVE LOGITS

pee

1.12

bies

0.98

bling

0.95

gee

0.94

EEE

0.92

zer

0.91

ples

0.91

zie

0.91

bles

0.91

zing

0.90

Activations Density 0.026%

occurrences of the word "gee" or variations like "gees" and "Geeves"

words containing variations of the suffix "ee", particularly in names or titles

No Comments

No Known Activations