INDEX

Explanations

information related to cybersecurity, political scandals, and hacking activities

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal or regulatory matters

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

ãĤ¼ãĤ¦ãĤ¹

-0.78

thood

-0.70

 UCHIJ

-0.69

sg

-0.67

orthern

-0.64

obyl

-0.63

ige

-0.62

iership

-0.62

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.61

electric

-0.61

POSITIVE LOGITS

 redacted

1.00

DOJ

0.85

FBI

0.79

 disingen

0.78

 attorney

0.77

 Attorney

0.76

 Podesta

0.75

 phony

0.75

 asserted

0.75

 irony

0.74

Activations Density 1.571%

information related to cybersecurity, political scandals, and hacking activities

phrases related to legal or regulatory matters

No Comments

No Known Activations