INDEX

Explanations

words related to physical trauma and health conditions

oai_token-act-pair · gpt-3.5-turbo

references to trauma and its effects

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bye

-0.94

arius

-0.67

verages

-0.67

ramer

-0.66

ateur

-0.65

ovation

-0.65

ebus

-0.65

tarians

-0.65

endar

-0.65

holder

-0.64

POSITIVE LOGITS

 trauma

1.05

 inflicted

1.02

umatic

0.94

traumatic

0.93

 traumat

0.90

 traumatic

0.89

 wounds

0.86

 flashbacks

0.83

imaru

0.83

 incurred

0.82

Activations Density 0.029%

words related to physical trauma and health conditions

references to trauma and its effects

No Comments

No Known Activations