INDEX

Explanations

words related to dependencies and conditional outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases related to conditions or factors that determine outcomes

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

vision

-0.90

ãĥīãĥ©

-0.80

asar

-0.72

ãĥŃ

-0.71

ãĥİ

-0.71

nik

-0.70

tha

-0.67

anas

-0.67

çĦ

-0.67

 Bench

-0.66

POSITIVE LOGITS

ymm

0.86

ancy

0.83

 critically

0.81

 upon

0.81

 heavily

0.80

ants

0.76

ancies

0.75

ractor

0.73

awaru

0.71

encies

0.71

Activations Density 0.015%

words related to dependencies and conditional outcomes

phrases related to conditions or factors that determine outcomes

No Comments

No Known Activations