INDEX

Explanations

phrases related to political events or entities

oai_token-act-pair · gpt-3.5-turbo

references to political parties and sides in a debate or election context

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

aca

-0.71

athetic

-0.70

sections

-0.69

 Dialogue

-0.67

atible

-0.66

ect

-0.65

rome

-0.65

hips

-0.65

anth

-0.65

otti

-0.63

POSITIVE LOGITS

 claim

0.90

 successfully

0.79

 unsuccessfully

0.72

 capitalize

0.70

 contends

0.69

ãĥ³ãĤ¸

0.68

 contend

0.67

 control

0.67

 advertise

0.66

 possession

0.65

Activations Density 1.074%

phrases related to political events or entities

references to political parties and sides in a debate or election context

No Comments

No Known Activations