INDEX

Explanations

words related to receiving benefits or advantages

oai_token-act-pair · gpt-3.5-turbo

terms related to benefits and beneficiaries 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

 Opera

-0.70

 Hole

-0.63

Ou

-0.63

âĹı

-0.61

buck

-0.60

Ain

-0.58

 Leather

-0.58

 Mole

-0.58

 Dresden

-0.58

 Traps

-0.57

POSITIVE LOGITS

iciary

1.30

doms

1.03

ornia

1.01

actor

0.98

 benef

0.97

icial

0.97

benef

0.94

iam

0.91

ortunate

0.91

icient

0.90

Activations Density 0.033%

words related to receiving benefits or advantages

terms related to benefits and beneficiaries in various contexts

No Comments

No Known Activations