INDEX

Explanations

words related to specific ideologies or philosophical concepts, particularly those with an -ian or -ism suffix

oai_token-act-pair · gpt-3.5-turbo

words with the suffix "-ian" or similar

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

Downloadha

-1.19

drops

-0.90

pots

-0.89

bsite

-0.86

click

-0.84

pot

-0.82

lehem

-0.80

matched

-0.79

liga

-0.79

isSpecialOrderable

-0.79

POSITIVE LOGITS

Era

0.96

 Revival

0.96

 ancestors

0.88

 heritage

0.88

era

0.86

 Orthodox

0.85

 worldview

0.83

 ancestor

0.82

 hegemony

0.82

 grandmother

0.82

Activations Density 0.141%

words related to specific ideologies or philosophical concepts, particularly those with an -ian or -ism suffix

words with the suffix "-ian" or similar

No Comments

No Known Activations