INDEX

Explanations

references to arbitration processes or terms related to legal arbitration

oai_token-act-pair · gpt-3.5-turbo

terms related to arbitration and legal processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ulton

-0.84

eele

-0.82

mers

-0.77

ku

-0.72

ux

-0.70

aired

-0.70

oppable

-0.69

erton

-0.68

finger

-0.68

map

-0.68

POSITIVE LOGITS

 arbit

1.20

 tribunal

1.10

 arbitration

1.05

 Arbit

1.04

 Tribunal

0.96

 adjud

0.88

rarily

0.86

 proceedings

0.79

rary

0.78

rators

0.78

Activations Density 0.019%

references to arbitration processes or terms related to legal arbitration

terms related to arbitration and legal processes

No Comments

No Known Activations