INDEX

Explanations

phrases related to intellectual faculties or cognitive abilities

oai_token-act-pair · gpt-3.5-turbo

terms related to the brain and cognitive functions

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

 Rhod

-0.86

 Prosecut

-0.79

atern

-0.74

 Specific

-0.72

 Antiqu

-0.69

 Degree

-0.67

Department

-0.65

 Ascend

-0.64

 Prosecutor

-0.62

aternal

-0.61

POSITIVE LOGITS

fuck

1.03

buster

0.93

wash

0.86

ãĥĦ

0.84

 fart

0.84

share

0.83

geist

0.80

washed

0.80

iest

0.80

storms

0.80

Activations Density 0.077%

phrases related to intellectual faculties or cognitive abilities

terms related to the brain and cognitive functions

No Comments

No Known Activations