INDEX

Explanations

phrases or terms related to licensing

oai_token-act-pair · gpt-3.5-turbo

mentions of licensing and authorization in various professional contexts

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

adra

-0.84

ptions

-0.79

horn

-0.73

bags

-0.72

pt

-0.72

bag

-0.71

 Takeru

-0.70

arsity

-0.70

bows

-0.70

thal

-0.70

POSITIVE LOGITS

 tradem

0.90

 firearms

0.82

 licensed

0.79

ĨĴ

0.78

 nursing

0.77

 gambling

0.75

 practition

0.75

yne

0.74

 freel

0.73

 premises

0.73

Activations Density 0.037%

phrases or terms related to licensing

mentions of licensing and authorization in various professional contexts

No Comments

No Known Activations