INDEX

Explanations

mentions of "dogs" in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to dogs and their behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

afort

-0.65

Kul

-0.64

theless

-0.64

 Lauder

-0.62

 Hoff

-0.62

 Meier

-0.62

 capsule

-0.61

 handshake

-0.60

 negotiators

-0.59

 Levant

-0.59

POSITIVE LOGITS

ogging

1.22

gers

1.13

ogged

1.02

ogs

1.02

glers

0.96

warts

0.89

mire

0.87

ickets

0.83

ãĤĮ

0.81

ravings

0.79

Activations Density 0.006%

mentions of "dogs" in various contexts

terms related to dogs and their behaviors

No Comments

No Known Activations