INDEX

Explanations

mentions of specific events, reports, or years

oai_token-act-pair · gpt-3.5-turbo

key phrases related to significant stories or reports

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

heit

-0.81

alties

-0.78

illi

-0.73

ryu

-0.72

ANCE

-0.70

SPONSORED

-0.70

 contam

-0.69

abel

-0.69

Types

-0.68

ptr

-0.68

POSITIVE LOGITS

 saga

1.10

 affair

1.03

 debate

0.94

 aftermath

0.92

 conversation

0.91

 latest

0.91

 upcoming

0.90

0.88

 investigation

0.88

 debacle

0.88

Activations Density 0.513%

mentions of specific events, reports, or years

key phrases related to significant stories or reports

No Comments

No Known Activations