INDEX

Explanations

adjectives describing the degree or intensity of something

oai_token-act-pair · gpt-3.5-turbo

intensifiers or descriptors of extremity and severity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

¶æ

-0.66

ãĥīãĥ©ãĤ´ãĥ³

-0.65

OPS

-0.64

¦

-0.64

Ô

-0.60

ighth

-0.60

¸

-0.59

Pope

-0.59

 permitting

-0.58

zsche

-0.58

POSITIVE LOGITS

enos

0.81

amus

0.77

ranged

0.76

ense

0.74

eous

0.72

ocating

0.70

yip

0.70

!!!!!!!!

0.68

ciating

0.67

lly

0.65

Activations Density 0.096%

adjectives describing the degree or intensity of something

intensifiers or descriptors of extremity and severity

No Comments

No Known Activations