INDEX

Explanations

phrases related to coercion or being compelled to do something against one's will

oai_token-act-pair · gpt-3.5-turbo

instances of the word "forced" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

vironment

-0.68

ership

-0.65

rou

-0.64

iverpool

-0.64

Enh

-0.63

orkshire

-0.63

 Offense

-0.62

itect

-0.62

iosyncr

-0.60

amina

-0.59

POSITIVE LOGITS

 into

0.94

otom

0.90

 aback

0.84

untarily

0.80

 overtime

0.75

 onto

0.73

 shut

0.73

 offline

0.69

into

0.68

 INTO

0.68

Activations Density 0.049%

phrases related to coercion or being compelled to do something against one's will

instances of the word "forced" in various contexts

No Comments

No Known Activations