INDEX

Explanations

words related to security or protection

oai_token-act-pair · gpt-3.5-turbo

references to guards or security personnel

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

BLE

-0.84

ãĥ£

-0.75

 Springs

-0.68

izoph

-0.66

KEN

-0.66

MAP

-0.66

theless

-0.65

MED

-0.61

ctive

-0.60

sequent

-0.60

POSITIVE LOGITS

rail

0.97

men

0.87

heed

0.85

ages

0.84

 guard

0.83

 guarding

0.83

masters

0.81

maid

0.80

dog

0.79

llan

0.78

Activations Density 0.028%

words related to security or protection

references to guards or security personnel

No Comments

No Known Activations