INDEX

Explanations

phrases related to a specific person's actions or experiences, such as activities, roles, or events they were involved in

oai_token-act-pair · gpt-3.5-turbo

mentions of the pronoun "his" along with temporal references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Canaver

-0.69

coins

-0.68

onyms

-0.65

eers

-0.65

soType

-0.63

facts

-0.62

pie

-0.62

zyme

-0.61

encers

-0.61

daq

-0.61

POSITIVE LOGITS

 tenure

1.32

 stint

1.28

 travels

1.21

 journey

1.10

 lifetime

1.05

 introductory

1.05

 visits

1.05

 visit

1.05

 brief

1.02

 journeys

1.02

Activations Density 0.143%

phrases related to a specific person's actions or experiences, such as activities, roles, or events they were involved in

mentions of the pronoun "his" along with temporal references

No Comments

No Known Activations