INDEX

Explanations

words related to cause and effect relationships

oai_token-act-pair · gpt-3.5-turbo

references to various effects, particularly in scientific or analytical 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

 pigeon

-0.69

 Standards

-0.67

 Timber

-0.62

 Pitch

-0.62

mbuds

-0.60

yne

-0.60

Dud

-0.60

 Jump

-0.59

 rooft

-0.58

 quarters

-0.58

POSITIVE LOGITS

iveness

1.23

uated

1.15

uating

1.06

ively

1.06

ually

1.04

ual

1.01

effects

0.99

uel

0.98

uate

0.98

uation

0.97

Activations Density 0.032%

words related to cause and effect relationships

references to various effects, particularly in scientific or analytical contexts

No Comments

No Known Activations