INDEX

Explanations

words related to legal terms and educational institutions

oai_token-act-pair · gpt-3.5-turbo

references to fictional characters and narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Versus

-0.49

 revisions

-0.47

 proactive

-0.46

 withdrawals

-0.46

 Tunnel

-0.45

 disruptive

-0.45

 unilateral

-0.44

 Collider

-0.44

 interim

-0.44

 inaction

-0.44

POSITIVE LOGITS

onica

0.59

berries

0.53

uca

0.48

imedia

0.48

itives

0.48

forts

0.47

 herself

0.47

iae

0.47

yt

0.47

amate

0.47

Activations Density 1.637%

words related to legal terms and educational institutions

references to fictional characters and narratives

No Comments

No Known Activations