INDEX

Explanations

mentions of negotiation-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to negotiation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

osate

-1.07

onso

-0.90

adder

-0.84

alach

-0.83

arton

-0.79

gart

-0.77

hemy

-0.74

laughter

-0.73

shine

-0.71

aston

-0.70

POSITIVE LOGITS

 agreements

1.00

 negotiated

0.99

 negotiation

0.98

 negotiator

0.97

 negotiations

0.96

 negotiators

0.95

 negotiating

0.84

 bargain

0.83

 negotiate

0.83

 negoti

0.82

Activations Density 0.042%

mentions of negotiation-related terms

terms related to negotiation processes

No Comments

No Known Activations