INDEX

Explanations

occurrences of the word "Allegations" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to allegations

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

bom

-0.73

 Wilde

-0.69

NetMessage

-0.68

OPLE

-0.67

ggle

-0.66

pox

-0.64

nown

-0.62

pins

-0.61

ModLoader

-0.61

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.61

POSITIVE LOGITS

edly

1.38

heny

1.31

iance

1.20

ations

1.03

iant

0.99

iances

0.96

orical

0.93

rett

0.87

ict

0.87

orial

0.86

Activations Density 0.018%

occurrences of the word "Allegations" or variations of it

references to allegations

No Comments

No Known Activations