INDEX

Explanations

words related to social welfare programs, particularly Social Security

oai_token-act-pair · gpt-3.5-turbo

references to social security programs

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

nces

-0.75

Äĩ

-0.74

è¦ļéĨĴ

-0.67

 needless

-0.67

oning

-0.66

 ridden

-0.64

mares

-0.64

ilts

-0.63

 Twain

-0.63

 Shannon

-0.63

POSITIVE LOGITS

Flow

0.82

Registration

0.78

 Security

0.78

Health

0.77

 Equality

0.77

Work

0.75

ists

0.74

Social

0.74

 Advisor

0.73

 Forces

0.73

Activations Density 0.012%

words related to social welfare programs, particularly Social Security

references to social security programs

No Comments

No Known Activations