INDEX

Explanations

In this case, the main thing this neuron does is find occurrences related to violent incidents

oai_token-act-pair · gpt-3.5-turbo

references to violent incidents and legal cases

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

 brakes

-0.97

aughs

-0.81

 buttons

-0.68

tics

-0.64

reci

-0.64

ient

-0.64

 views

-0.62

iences

-0.62

ostics

-0.62

 revolutions

-0.60

POSITIVE LOGITS

 spree

0.85

 spanning

0.77

 involving

0.74

 costing

0.72

 riddled

0.71

ĸļ

0.70

 totaling

0.69

 guiActiveUnfocused

0.69

 overseen

0.68

cap

0.68

Activations Density 0.315%

In this case, the main thing this neuron does is find occurrences related to violent incidents

references to violent incidents and legal cases

No Comments

No Known Activations