INDEX

Explanations

words related to influence, control, and shaping

oai_token-act-pair · gpt-3.5-turbo

concepts related to influence and shaping outcomes or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

BuyableInstoreAndOnline

-0.79

osaurs

-0.79

False

-0.72

audi

-0.70

ubs

-0.69

©¶æ¥µ

-0.69

Sham

-0.69

sels

-0.68

kies

-0.67

iss

-0.66

POSITIVE LOGITS

how

1.41

 shaping

1.16

 outcomes

1.16

 whether

1.12

 perceptions

1.10

 decisions

1.09

 outcome

1.03

 destiny

1.02

 behaviour

1.01

 behavior

0.98

Activations Density 0.197%

words related to influence, control, and shaping

concepts related to influence and shaping outcomes or behaviors

No Comments

No Known Activations