INDEX

Explanations

words related to negative consequences or actions

oai_token-act-pair · gpt-3.5-turbo

themes related to health, financial issues, and socio-political challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 depress

-0.50

pop

-0.48

cknow

-0.47

going

-0.46

 studied

-0.46

ifted

-0.46

 hail

-0.44

cknowled

-0.44

beh

-0.44

enne

-0.43

POSITIVE LOGITS

0.55

 ashore

0.54

ylum

0.54

ocobo

0.54

 Afgh

0.53

 whilst

0.53

Reloaded

0.51

 Salvador

0.51

Eva

0.50

ãĢĤ

0.50

Activations Density 1.191%

words related to negative consequences or actions

themes related to health, financial issues, and socio-political challenges

No Comments

No Known Activations