INDEX

Explanations

keywords related to controversial and impactful events such as scandals, investigations, incidents, and shutdowns

oai_token-act-pair · gpt-3.5-turbo

terms related to controversies and significant events

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

requisite

-0.74

ordinate

-0.70

Higher

-0.70

rake

-0.66

POSE

-0.66

asonable

-0.65

usually

-0.65

ailable

-0.64

atin

-0.64

ucl

-0.63

POSITIVE LOGITS

 debacle

1.01

 fiasco

0.90

 spree

0.85

naires

0.79

 bandwagon

0.78

naire

0.76

 Tracker

0.76

 Rebellion

0.71

AMC

0.70

undrum

0.69

Activations Density 0.387%

keywords related to controversial and impactful events such as scandals, investigations, incidents, and shutdowns

terms related to controversies and significant events

No Comments

No Known Activations