INDEX

Explanations

words related to transmission of data or information

oai_token-act-pair · gpt-3.5-turbo

terms related to the transmission of data or information

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

anova

-0.89

atti

-0.86

este

-0.81

 Alban

-0.79

anka

-0.74

liga

-0.73

arist

-0.71

gger

-0.70

stad

-0.70

redo

-0.67

POSITIVE LOGITS

 transmissions

1.00

 transmit

0.96

 transmitter

0.95

 transmitting

0.92

 transmitted

0.89

ters

0.87

 signals

0.84

ceiver

0.82

mitter

0.81

imental

0.80

Activations Density 0.053%

words related to transmission of data or information

terms related to the transmission of data or information

No Comments

No Known Activations