INDEX

Explanations

conditional statements or hypothetical scenarios that include "would."

oai_token-act-pair · gpt-3.5-turbo

phrases containing the word "would."

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

building

-0.67

rylic

-0.66

Kag

-0.65

resources

-0.64

Times

-0.61

 Seoul

-0.60

story

-0.60

 Modified

-0.59

meta

-0.59

holder

-0.58

POSITIVE LOGITS

be

0.92

 surely

0.90

 ideally

0.86

 doubtless

0.84

 undoubtedly

0.83

 otherwise

0.83

ÃĥÃĤ

0.81

 probably

0.81

 suffice

0.81

ĸļ

0.81

Activations Density 0.146%

conditional statements or hypothetical scenarios that include "would."

phrases containing the word "would."

No Comments

No Known Activations