INDEX

Explanations

links or associations between entities or individuals

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate connections or relationships to various topics or individuals

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

Letter

-0.78

iae

-0.77

headers

-0.71

icer

-0.70

 faced

-0.70

 snipp

-0.69

Reply

-0.69

tif

-0.67

URES

-0.67

engine

-0.66

POSITIVE LOGITS

 Haiti

0.73

 haunt

0.69

 criminality

0.69

 terrorism

0.69

Ong

0.67

 Citizens

0.65

 mainland

0.64

 Bermuda

0.63

 Wikileaks

0.63

 Autism

0.63

Activations Density 0.104%

links or associations between entities or individuals

phrases that indicate connections or relationships to various topics or individuals

No Comments

No Known Activations