INDEX

Explanations

terms related to clusters, particularly mentioning the word "cluster" several times at varying activations

oai_token-act-pair · gpt-3.5-turbo

references to "clusters," indicating groupings in various contexts

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

hran

-0.80

Ö¼

-0.76

ODUCT

-0.68

PLIED

-0.68

orters

-0.68

inen

-0.67

toc

-0.67

inburgh

-0.67

tek

-0.65

ebus

-0.65

POSITIVE LOGITS

fuck

1.15

bom

0.96

usters

0.91

 clusters

0.89

 cluster

0.84

mates

0.77

 geographically

0.72

 headaches

0.71

 clustered

0.69

 grouping

0.68

Activations Density 0.031%

terms related to clusters, particularly mentioning the word "cluster" several times at varying activations

references to "clusters," indicating groupings in various contexts

No Comments

No Known Activations