INDEX

Explanations

words related to support or reinforcement

oai_token-act-pair · gpt-3.5-turbo

terms related to support and enhancement

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

 flaw

-0.68

andro

-0.68

 PARK

-0.68

holes

-0.65

iott

-0.61

æ³

-0.61

viol

-0.60

Ðº

-0.60

 pertaining

-0.59

wear

-0.58

POSITIVE LOGITS

 morale

0.87

 coffers

0.81

ifully

0.79

emonic

0.73

 bolster

0.73

enance

0.72

 buoy

0.69

 confidence

0.68

geries

0.68

glers

0.67

Activations Density 0.098%

words related to support or reinforcement

terms related to support and enhancement

No Comments

No Known Activations