INDEX

Explanations

words related to physical traumas and medical conditions

oai_token-act-pair · gpt-3.5-turbo

terms related 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bye

-0.86

sheet

-0.71

mate

-0.67

ramer

-0.66

holder

-0.64

ership

-0.63

arius

-0.63

ovation

-0.62

ateur

-0.62

arten

-0.61

POSITIVE LOGITS

 inflicted

1.04

 trauma

0.96

umatic

0.93

traumatic

0.91

 traumat

0.87

stress

0.81

 suffered

0.79

 incurred

0.79

 traumatic

0.78

imaru

0.77

Activations Density 0.022%

words related to physical traumas and medical conditions

terms related to trauma and its effects

No Comments

No Known Activations