INDEX

Explanations

words related to leaks or leakage

oai_token-act-pair · gpt-3.5-turbo

references to leaks in various 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

iterranean

-0.91

HCR

-0.63

 Dragons

-0.62

=-=-=-=-

-0.62

;;;;;;;;

-0.61

zees

-0.61

arching

-0.60

eele

-0.60

ieval

-0.60

 Gentle

-0.59

POSITIVE LOGITS

inventoryQuantity

0.84

 leaks

0.78

 leak

0.78

 leaking

0.78

Leaks

0.76

acious

0.75

 leakage

0.74

0.72

rets

0.72

worthiness

0.72

Activations Density 0.015%

words related to leaks or leakage

references to leaks in various contexts

No Comments

No Known Activations