INDEX

Explanations

phrases related to policies, regulations, and governmental actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

eno

-0.81

aba

-0.71

ceive

-0.67

leeve

-0.67

thood

-0.66

rehend

-0.64

bg

-0.64

ade

-0.63

earch

-0.62

imi

-0.61

POSITIVE LOGITS

 latter

1.14

 biggest

1.09

resa

1.08

 largest

1.06

oret

1.06

 fastest

1.05

 oldest

1.05

 slightest

1.04

 simplest

1.03

 smallest

1.00

Activations Density 0.679%

phrases related to policies, regulations, and governmental actions

occurrences of the word "the."

No Comments

No Known Activations