INDEX

Explanations

special characters used to emphasize or express strong emotions

oai_token-act-pair · gpt-3.5-turbo

repeated symbols or characters within the text

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

 fishes

-0.76

 welf

-0.74

 greens

-0.71

ãĥ¼ãĥĨãĤ£

-0.70

 indemn

-0.68

pped

-0.67

 adulthood

-0.65

 charger

-0.65

 nodd

-0.65

 laun

-0.65

POSITIVE LOGITS

they

1.01

WHERE

1.00

yet

0.99

wait

0.96

BUT

0.94

etc

0.91

there

0.90

why

0.88

where

0.87

yeah

0.86

Activations Density 0.039%

special characters used to emphasize or express strong emotions

repeated symbols or characters within the text

No Comments

No Known Activations