INDEX

Explanations

mentions of legal or administrative terms related to judgment or authority

oai_token-act-pair · gpt-3.5-turbo

terms related to illustration and arbitration

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

Downloadha

-0.80

 Leap

-0.67

 palms

-0.67

ipple

-0.67

 Toast

-0.66

OHN

-0.65

 grip

-0.64

 Sense

-0.62

ãĥīãĥ©ãĤ´ãĥ³

-0.62

 Brach

-0.62

POSITIVE LOGITS

rator

1.53

ration

1.48

rative

1.43

rations

1.34

rators

1.33

rat

1.20

rates

1.19

rated

1.17

rating

1.17

rary

1.11

Activations Density 0.085%

mentions of legal or administrative terms related to judgment or authority

terms related to illustration and arbitration

No Comments

No Known Activations