INDEX

Explanations

adjectives and descriptions suggesting a certain quality or characteristic

oai_token-act-pair · gpt-3.5-turbo

descriptive adjectives that convey negative qualities or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

abwe

-0.77

osponsors

-0.69

MK

-0.67

CF

-0.65

 notably

-0.65

amera

-0.64

ocked

-0.64

uilding

-0.63

BW

-0.63

 concentrating

-0.63

POSITIVE LOGITS

est

1.71

liest

1.37

iest

1.15

hest

1.14

ness

1.13

 culmination

0.98

 truth

0.97

 thing

0.96

EST

0.96

 conclusion

0.96

Activations Density 0.251%

adjectives and descriptions suggesting a certain quality or characteristic

descriptive adjectives that convey negative qualities or experiences

No Comments

No Known Activations