INDEX

Explanations

instances of actions or characteristics tied to a group of people

oai_token-act-pair · gpt-3.5-turbo

the verb "are" and its forms used in various contexts

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

pedia

-0.63

 Which

-0.61

 Rout

-0.60

ricks

-0.60

ffe

-0.60

ooters

-0.59

Â¨

-0.59

ization

-0.58

 apology

-0.57

 Solution

-0.56

POSITIVE LOGITS

wolves

0.91

 supposed

0.78

nt

0.77

tein

0.73

held

0.68

wolf

0.68

 supposedly

0.68

 married

0.68

 subscribed

0.67

 behold

0.67

Activations Density 0.201%

instances of actions or characteristics tied to a group of people

the verb "are" and its forms used in various contexts

No Comments

No Known Activations