INDEX

Explanations

entries mentioning "Mladic" with varying degrees of relevance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lad" and its variations in context

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

ELL

-0.86

forts

-0.73

ModLoader

-0.70

lished

-0.69

 Bakr

-0.67

ä¸Ń

-0.66

oldown

-0.66

 ticking

-0.66

kward

-0.66

PDATE

-0.66

POSITIVE LOGITS

imir

1.37

der

1.03

itional

0.88

mir

0.86

isl

0.86

ynam

0.85

iamond

0.82

itionally

0.81

rian

0.78

Tid

0.78

Activations Density 0.017%

entries mentioning "Mladic" with varying degrees of relevance

occurrences of the word "lad" and its variations in context

No Comments

No Known Activations