INDEX

Explanations

phrases related to the concept of liberty

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "liberty" or "liberals."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 tasting

-0.78

 retreat

-0.68

 mamm

-0.68

 clad

-0.67

 stroke

-0.67

 breath

-0.66

avorite

-0.65

 sliding

-0.65

 dust

-0.63

 reflecting

-0.62

POSITIVE LOGITS

ator

1.14

ation

1.11

ī

1.08

iment

1.06

Ģ

1.06

alis

1.05

ating

1.05

ated

1.04

als

1.02

ational

1.02

Activations Density 0.081%

phrases related to the concept of liberty

words related to the concept of "liberty" or "liberals."

No Comments

No Known Activations