INDEX

Explanations

words related to specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

prominent names and specific numerical references

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

igate

-0.76

______

-0.71

Victoria

-0.66

ORK

-0.64

tnc

-0.64

$$$$

-0.63

)",

-0.62

igm

-0.62

elfare

-0.61

;;;;

-0.61

POSITIVE LOGITS

 nonetheless

1.41

 nevertheless

1.13

etheless

1.08

 persists

1.02

 retains

0.95

 persisted

0.92

 insists

0.86

 lacks

0.84

 hasn

0.80

 disagrees

0.79

Activations Density 0.469%

words related to specific individuals or entities

prominent names and specific numerical references

No Comments

No Known Activations