INDEX

Explanations

phrases related to political figures and locations

oai_token-act-pair · gpt-3.5-turbo

mentions of government entities and significant geopolitical references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

azard

-0.58

aples

-0.58

pires

-0.57

rocal

-0.55

roup

-0.55

nance

-0.54

erenn

-0.52

ibaba

-0.52

ablish

-0.51

merce

-0.51

POSITIVE LOGITS

_.

0.82

ãĢĤ

0.80

 instead

0.78

!.

0.77

 anymore

0.73

ðŁĺ

0.72

 ASAP

0.71

?????

0.70

?,

0.69

Activations Density 0.991%

phrases related to political figures and locations

mentions of government entities and significant geopolitical references

No Comments

No Known Activations