INDEX

Explanations

references to customer service interactions

oai_token-act-pair · gpt-3.5-turbo

mentions of customer service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hift

-0.93

lahoma

-0.77

hran

-0.77

uits

-0.75

pots

-0.74

ooks

-0.74

orb

-0.73

chool

-0.73

outhern

-0.73

perm

-0.70

POSITIVE LOGITS

 service

1.03

 satisfaction

0.96

 relations

0.90

 testim

0.88

 SERVICE

0.86

service

0.84

 feedback

0.82

atical

0.81

 Satisf

0.78

 engagement

0.78

Activations Density 0.066%

references to customer service interactions

mentions of customer service

No Comments

No Known Activations