INDEX

Explanations

terms related to a specific organization or entity abbreviated as "TE."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "TE" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĥãĥĪ

-0.80

iewicz

-0.75

espie

-0.74

andise

-0.73

circ

-0.72

 teasp

-0.69

ctrl

-0.67

 airlines

-0.67

mingham

-0.67

raviolet

-0.66

POSITIVE LOGITS

ACH

1.02

aching

1.02

TE

0.96

LE

0.95

brate

0.94

TI

0.92

achers

0.92

achable

0.91

chnology

0.90

levision

0.88

Activations Density 0.008%

terms related to a specific organization or entity abbreviated as "TE."

occurrences of the abbreviation "TE" in various contexts

No Comments

No Known Activations