INDEX

Explanations

the phrase "what exactly" indicating a request for clarification or detail

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

questions asking for a specific explanation or detail

oai_token-act-pair · gpt-3.5-turbo

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

ĸļ

-0.76

NYSE

-0.67

puter

-0.67

gra

-0.63

 newsletters

-0.62

WAYS

-0.61

sha

-0.60

gi

-0.59

«ĺ

-0.59

-0.58

POSITIVE LOGITS

 transpired

1.05

 separates

0.97

 distinguishes

0.94

soever

0.88

 happened

0.84

 differs

0.84

 entails

0.84

 happens

0.81

 constitutes

0.81

 awaits

0.79

Activations Density 0.036%

the phrase "what exactly" indicating a request for clarification or detail

questions asking for a specific explanation or detail

No Comments

No Known Activations