INDEX

Explanations

verbs related to actions or processes

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing ongoing actions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 ..............

-0.65

ichita

-0.63

option

-0.63

so

-0.60

 Brigham

-0.60

 envy

-0.60

utch

-0.57

 PayPal

-0.55

 request

-0.55

gif

-0.55

POSITIVE LOGITS

 oneself

0.77

olphin

0.71

 Blaster

0.66

ebus

0.64

utical

0.63

 Scientist

0.60

orously

0.60

redients

0.60

umenthal

0.60

ilda

0.60

Activations Density 0.070%

verbs related to actions or processes

phrases emphasizing ongoing actions or states of being

No Comments

No Known Activations