INDEX

Explanations

adjectives and nouns related to unique or exceptional characteristics

oai_token-act-pair · gpt-3.5-turbo

nouns and terms related to roles, positions, and actions

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

assies

-0.83

 strawberries

-0.74

rollers

-0.73

idents

-0.70

ainers

-0.68

CLR

-0.67

iries

-0.64

amate

-0.63

mins

-0.63

 Roads

-0.62

POSITIVE LOGITS

 akin

0.85

 euphem

0.77

nown

0.69

 hallmark

0.69

ually

0.68

 likened

0.67

 adaptation

0.66

 tactic

0.65

 precaution

0.65

 testament

0.65

Activations Density 0.165%

adjectives and nouns related to unique or exceptional characteristics

nouns and terms related to roles, positions, and actions

No Comments

No Known Activations