INDEX

Explanations

phrases related to causation or explanation using the word "because."

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

vernment

-0.76

dale

-0.67

advertising

-0.67

DB

-0.66

ira

-0.64

mares

-0.63

ancer

-0.62

ojure

-0.60

shaw

-0.59

edia

-0.58

POSITIVE LOGITS

 result

1.35

 same

1.31

same

1.21

 culmination

1.13

ologically

1.12

 ones

1.10

 envy

1.09

 equivalent

1.08

 hardest

1.06

 easiest

1.01

Activations Density 0.137%

phrases related to causation or explanation using the word "because."

repetitive mentions of the word "the."

No Comments

No Known Activations