INDEX

Explanations

words and phrases related to communication, such as "spoke with", "talked to", and "texted with"

oai_token-act-pair · gpt-3.5-turbo

instances of personal communication or interactions

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

 perish

-0.72

 recy

-0.70

 disproportionately

-0.67

Quantity

-0.65

 spawns

-0.64

 gore

-0.64

 itself

-0.64

 Inher

-0.64

 Explosion

-0.63

ocaust

-0.63

POSITIVE LOGITS

fax

0.91

 briefed

0.85

 requesting

0.79

 Kislyak

0.78

 confir

0.78

 inquire

0.76

rompt

0.76

olicited

0.75

arre

0.75

 texted

0.74

Activations Density 0.745%

words and phrases related to communication, such as "spoke with", "talked to", and "texted with"

instances of personal communication or interactions

No Comments

No Known Activations