INDEX

Explanations

phrases indicating a decision or inclination to stay in a specific situation or place

oai_token-act-pair · gpt-3.5-turbo

instances of the word "remain" in various contexts

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

ramid

-0.76

 Relief

-0.72

ongyang

-0.71

isson

-0.70

rote

-0.67

DIT

-0.65

ologies

-0.63

oglobin

-0.63

 Circuit

-0.62

¶ħ

-0.61

POSITIVE LOGITS

 unchanged

1.04

 afloat

0.95

 intact

0.91

 silent

0.86

 undecided

0.86

 steadfast

0.85

 undefeated

0.82

 unanswered

0.82

 undet

0.82

 unaffected

0.78

Activations Density 0.035%

phrases indicating a decision or inclination to stay in a specific situation or place

instances of the word "remain" in various contexts

No Comments

No Known Activations