INDEX

Explanations

words related to important decisions, discussions, or changes

oai_token-act-pair · gpt-3.5-turbo

terms related to political discourse and systemic change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

NetMessage

-0.87

annot

-0.72

ãĥŃ

-0.62

ailability

-0.60

Ô

-0.57

ADRA

-0.56

abad

-0.56

oln

-0.55

Ble

-0.55

 blat

-0.55

POSITIVE LOGITS

osphere

0.99

ifice

0.94

iest

0.87

enium

0.85

 accordingly

0.82

 anew

0.77

 portion

0.73

clock

0.72

 fallacy

0.70

 ahead

0.69

Activations Density 0.369%

words related to important decisions, discussions, or changes

terms related to political discourse and systemic change

No Comments

No Known Activations