INDEX

Explanations

Keywords related to actions or events that occurred prior to a specific point in time

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prior" indicating previous events or actions

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

aden

-0.77

rosso

-0.73

asp

-0.71

RO

-0.68

Baby

-0.68

%%%%

-0.66

ickle

-0.63

Hub

-0.63

romeda

-0.63

mad

-0.62

POSITIVE LOGITS

itiz

1.23

itized

1.11

etheless

1.09

ities

1.06

ebin

0.84

icip

0.82

ITY

0.77

ĨĴ

0.75

ĸļ

0.75

emort

0.71

Activations Density 0.023%

Keywords related to actions or events that occurred prior to a specific point in time

instances of the word "prior" indicating previous events or actions

No Comments

No Known Activations