INDEX

Explanations

instances of the word "it" followed by a verb

oai_token-act-pair · gpt-3.5-turbo

phrases that discuss the conditionality or alternatives in various situations

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

 Ratio

-0.65

 Disclosure

-0.62

;;;;;;;;;;;;

-0.60

 Syndrome

-0.58

 Irwin

-0.58

 Amen

-0.57

uda

-0.56

 Rating

-0.56

ilib

-0.56

 Contents

-0.56

POSITIVE LOGITS

oots

0.73

vg

0.68

 wisely

0.67

 consciously

0.66

theless

0.64

rha

0.63

ween

0.62

 advoc

0.60

 intentional

0.59

racuse

0.59

Activations Density 0.094%

instances of the word "it" followed by a verb

phrases that discuss the conditionality or alternatives in various situations

No Comments

No Known Activations