INDEX

Explanations

terms related to insurance policy premiums

oai_token-act-pair · gpt-3.5-turbo

specific terms related to insurance premiums

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

 Dynam

-0.76

tons

-0.71

gdala

-0.71

URA

-0.71

OTE

-0.70

UE

-0.70

Suc

-0.69

 Liberation

-0.69

nan

-0.68

 Alam

-0.68

POSITIVE LOGITS

 premiums

1.29

amacare

0.99

 reimburse

0.83

 repeal

0.81

 adjust

0.80

 insurance

0.79

 insurer

0.79

 insurers

0.79

igans

0.79

 incurred

0.79

Activations Density 0.032%

terms related to insurance policy premiums

specific terms related to insurance premiums

No Comments

No Known Activations