INDEX

Explanations

phrases related to abusive or harmful situations and mental health struggles

oai_token-act-pair · gpt-3.5-turbo

themes related to abuse and mental health struggles

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

 slic

-0.79

 meteor

-0.75

£ı

-0.74

ouver

-0.74

 Manufact

-0.72

VEL

-0.71

 printers

-0.69

 manned

-0.68

 revolutions

-0.68

 imports

-0.68

POSITIVE LOGITS

 counselling

1.15

 counselors

1.15

 trauma

1.07

 counselor

1.04

 counseling

1.04

 traumatic

1.02

ilitating

1.02

endered

0.99

 therapy

0.98

abuse

0.97

Activations Density 0.288%

phrases related to abusive or harmful situations and mental health struggles

themes related to abuse and mental health struggles

No Comments

No Known Activations