INDEX

Explanations

phrases related to guidance and leadership

oai_token-act-pair · gpt-3.5-turbo

words related to identification and categorization

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

 Nova

-0.62

js

-0.61

ãĥĥãĥĪ

-0.59

acity

-0.58

ga

-0.58

addons

-0.58

ks

-0.58

jet

-0.57

ko

-0.57

sax

-0.56

POSITIVE LOGITS

ING

1.52

ULAR

1.42

ER

1.40

IES

1.40

ED

1.39

ANT

1.37

IENT

1.36

NER

1.35

ERS

1.35

EST

1.35

Activations Density 0.162%

phrases related to guidance and leadership

words related to identification and categorization

No Comments

No Known Activations