INDEX

Explanations

words related to locations and geographic entities

oai_token-act-pair · gpt-3.5-turbo

specific names and terms related to places, people, and actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pedia

-0.59

è¦ļéĨĴ

-0.55

pmwiki

-0.55

oidal

-0.51

minster

-0.49

ãĤ¨ãĥ«

-0.48

racuse

-0.47

soft

-0.47

 unfocusedRange

-0.46

AGES

-0.45

POSITIVE LOGITS

there

0.55

 thereof

0.50

charg

0.46

aura

0.45

have

0.45

ah

0.44

arming

0.44

both

0.43

husband

0.43

aries

0.42

Activations Density 0.405%

words related to locations and geographic entities

specific names and terms related to places, people, and actions

No Comments

No Known Activations