INDEX

Explanations

rhetorical questions emphasizing uncertainty or concern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

quartered

-0.84

inous

-0.70

esta

-0.68

una

-0.68

ificant

-0.67

iquette

-0.66

gest

-0.65

à¨

-0.65

cipled

-0.65

stem

-0.64

POSITIVE LOGITS

 Wouldn

1.47

 Suppose

1.28

 Surely

1.26

 Would

1.23

 Could

1.09

 Imagine

1.04

 Turns

1.02

 Maybe

1.01

 Well

1.01

Isn

0.98

Activations Density 0.057%

rhetorical questions emphasizing uncertainty or concern

No Comments

No Known Activations