INDEX

Explanations

phrases related to names ending in "os."

oai_token-act-pair · gpt-3.5-turbo

the term "os" as it relates to a medical or biological context

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

OWS

-0.70

OUT

-0.68

taker

-0.68

 grounds

-0.64

ufact

-0.63

bler

-0.61

è¦ļéĨĴ

-0.61

ãĥ¬

-0.61

ãĤ¡

-0.60

lished

-0.58

POSITIVE LOGITS

hiba

1.48

ophical

1.17

opher

1.12

heet

1.08

omething

1.07

ophy

1.07

cano

1.05

sein

1.04

metics

1.04

aurus

1.03

Activations Density 0.034%

phrases related to names ending in "os."

the term "os" as it relates to a medical or biological context

No Comments

No Known Activations