INDEX

Explanations

references to inquiries or investigations

oai_token-act-pair · gpt-3.5-turbo

words related to inquiries and investigations

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

nown

-0.72

board

-0.70

enburg

-0.68

fell

-0.67

perm

-0.67

 Depend

-0.66

 Tycoon

-0.61

stadt

-0.61

amera

-0.60

berman

-0.60

POSITIVE LOGITS

 probing

1.12

iry

1.08

iries

1.05

isition

1.03

 inquire

1.02

 inqu

1.01

 Inqu

1.00

naires

0.98

isitions

0.93

 inquiry

0.92

Activations Density 0.052%

references to inquiries or investigations

words related to inquiries and investigations

No Comments

No Known Activations