INDEX

Explanations

mentions of "Mueller" in a text

oai_token-act-pair · gpt-3.5-turbo

mentions of Robert Mueller

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

piring

-0.77

Pyr

-0.77

lihood

-0.76

 Hawaiian

-0.76

ential

-0.72

 Samurai

-0.70

 Zoro

-0.69

 Filipino

-0.68

itarian

-0.67

points

-0.67

POSITIVE LOGITS

 Mueller

1.22

ueller

1.00

 indict

0.78

 dossier

0.77

 investigating

0.77

andowski

0.76

owitz

0.76

enthal

0.75

schild

0.75

 bund

0.74

Activations Density 0.011%

mentions of "Mueller" in a text

mentions of Robert Mueller

No Comments

No Known Activations