INDEX

Explanations

proper nouns related to geographical locations and government institutions

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographic locations and governmental entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ometimes

-0.86

esters

-0.74

rupulous

-0.71

hops

-0.69

rists

-0.69

uters

-0.69

writers

-0.68

orry

-0.67

 dstg

-0.66

utterstock

-0.66

POSITIVE LOGITS

wide

0.99

's

0.83

 residency

0.77

abl

0.76

 presidency

0.76

 anew

0.72

 Seal

0.71

 anthem

0.69

Wide

0.68

 Presidency

0.68

Activations Density 0.595%

proper nouns related to geographical locations and government institutions

mentions of specific geographic locations and governmental entities

No Comments

No Known Activations