INDEX

Explanations

dates and time-related words or phrases

oai_token-act-pair · gpt-3.5-turbo

instances of temporal phrases indicating specific milestones or events

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

 plurality

-0.73

 sails

-0.70

 observer

-0.63

 spin

-0.62

 wipe

-0.60

options

-0.59

 assume

-0.58

BDS

-0.57

 pinch

-0.57

 lawn

-0.57

POSITIVE LOGITS

atto

0.72

nen

0.71

 Cert

0.69

ued

0.67

govtrack

0.67

erest

0.65

adh

0.64

 fitting

0.64

onda

0.62

xus

0.61

Activations Density 0.154%

dates and time-related words or phrases

instances of temporal phrases indicating specific milestones or events

No Comments

No Known Activations