INDEX

Explanations

descriptions of people and their actions

oai_token-act-pair · gpt-3.5-turbo

concepts related to social justice and inequality

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

]).

-0.63

SPONSORED

-0.59

>]

-0.57

Gene

-0.57

Auth

-0.57

]),

-0.56

arthed

-0.55

})

-0.54

Ħ¢

-0.54

Last

-0.53

POSITIVE LOGITS

 however

0.54

 flatt

0.54

 though

0.53

 everywhere

0.50

 meanwhile

0.49

ometimes

0.47

 insofar

0.47

 ital

0.47

 orphans

0.47

 subdiv

0.46

Activations Density 2.100%

descriptions of people and their actions

concepts related to social justice and inequality

No Comments

No Known Activations