INDEX

Explanations

phrases related to reminders or recollections

oai_token-act-pair · gpt-3.5-turbo

terms related to reminders and notifications

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

keye

-0.77

hair

-0.76

enne

-0.74

erate

-0.74

annis

-0.74

inion

-0.72

anova

-0.71

asus

-0.70

quer

-0.70

oct

-0.68

POSITIVE LOGITS

 reminder

1.25

 reminders

1.22

 reminding

0.85

 remind

0.78

 marking

0.77

 marker

0.76

ariat

0.69

 prompts

0.68

 forgetting

0.68

 acknowledgment

0.67

Activations Density 0.020%

phrases related to reminders or recollections

terms related to reminders and notifications

No Comments

No Known Activations