INDEX

Explanations

occurrences of organizations or entities followed by the term "Trust"

oai_token-act-pair · gpt-3.5-turbo

mentions of various trusts and organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

OPLE

-0.79

oths

-0.72

neapolis

-0.67

pmwiki

-0.67

Ð¼

-0.64

ktop

-0.63

hyde

-0.63

undown

-0.62

ãĥ©ãĥ³

-0.62

OPA

-0.62

POSITIVE LOGITS

ees

1.21

worthiness

1.11

 Trust

1.08

worthy

1.01

ee

0.95

ty

0.92

ership

0.91

eous

0.82

terness

0.82

rition

0.81

Activations Density 0.009%

occurrences of organizations or entities followed by the term "Trust"

mentions of various trusts and organizations

No Comments

No Known Activations