INDEX

Explanations

trends or mentions of large amounts of people or items moving in or out of a location

oai_token-act-pair · gpt-3.5-turbo

terms related to large-scale movements of people or resources

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

Merit

-0.68

ovember

-0.68

verbs

-0.67

acter

-0.64

 Atomic

-0.64

zan

-0.64

tein

-0.64

deen

-0.64

ridges

-0.62

inav

-0.61

POSITIVE LOGITS

 influx

0.88

naires

0.86

 arrivals

0.83

glers

0.83

eson

0.83

uating

0.82

 flooding

0.81

naire

0.81

ãĥ¼ãĥĨãĤ£

0.80

oresc

0.77

Activations Density 0.027%

trends or mentions of large amounts of people or items moving in or out of a location

terms related to large-scale movements of people or resources

No Comments

No Known Activations