INDEX

Explanations

words related to pseudonyms or pseudoscience

oai_token-act-pair · gpt-3.5-turbo

terms related to pseudoscience and misleading claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 sights

-0.84

cakes

-0.84

cake

-0.84

 sight

-0.61

ilion

-0.60

 hearts

-0.60

 servicing

-0.59

 stakes

-0.59

brance

-0.58

hearted

-0.57

POSITIVE LOGITS

udo

1.08

udos

0.94

arial

0.89

atural

0.82

Pse

0.81

onymous

0.76

bull

0.75

onyms

0.75

crow

0.74

entials

0.72

Activations Density 0.028%

words related to pseudonyms or pseudoscience

terms related to pseudoscience and misleading claims

No Comments

No Known Activations