INDEX

Explanations

destructive actions or events

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cest

-0.79

 entertain

-0.67

Sol

-0.64

idth

-0.61

cal

-0.61

 entertained

-0.60

eq

-0.58

 Cele

-0.58

rosso

-0.58

ADV

-0.58

POSITIVE LOGITS

 mysteriously

0.72

 overnight

0.72

 catast

0.71

 proport

0.71

rift

0.70

 horribly

0.69

 charred

0.68

uddenly

0.68

 horrend

0.68

 Qiao

0.67

Activations Density 0.327%

destructive actions or events

No Comments

No Known Activations