INDEX

Explanations

verbs or phrases related to likelihood or possibility

oai_token-act-pair · gpt-3.5-turbo

conditional statements or speculations about various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iphate

-0.86

ankind

-0.67

 nomine

-0.66

imei

-0.65

hung

-0.64

rones

-0.64

athe

-0.64

hunt

-0.64

ierce

-0.64

mares

-0.63

POSITIVE LOGITS

 attributable

1.22

 indicative

1.19

due

1.16

 intentional

1.13

 coincidence

1.07

 because

0.99

 deliberate

0.97

 sympt

0.95

 owing

0.92

 unintentional

0.91

Activations Density 0.276%

verbs or phrases related to likelihood or possibility

conditional statements or speculations about various situations

No Comments

No Known Activations