INDEX

Explanations

phrases indicating a call to action or a request for a specific action to be taken

oai_token-act-pair · gpt-3.5-turbo

repetitive phrases or calls to action

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

VERTISEMENT

-0.91

©¶æ¥µ

-0.77

 âĶľâĶĢâĶĢ

-0.67

eah

-0.66

low

-0.66

rough

-0.64

 Ãľ

-0.63

LX

-0.63

ãĤª

-0.63

 Pend

-0.62

POSITIVE LOGITS

erous

1.01

 behalf

0.96

shore

0.84

 reinforcements

0.80

etimes

0.72

reb

0.72

 elders

0.70

unal

0.69

Downloadha

0.68

 circulation

0.68

Activations Density 0.045%

phrases indicating a call to action or a request for a specific action to be taken

repetitive phrases or calls to action

No Comments

No Known Activations