INDEX

Explanations

terms related to protection or defense against various threats

oai_token-act-pair · gpt-3.5-turbo

phrases related to protection or safeguarding against various threats

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ppa

-0.82

ynes

-0.80

ftime

-0.78

ICLE

-0.72

lator

-0.70

pause

-0.69

lishes

-0.69

 Introduced

-0.69

ruary

-0.68

cube

-0.67

POSITIVE LOGITS

 harm

1.06

 future

1.00

 impending

0.98

 intrusion

0.94

 deterioration

0.93

 dangers

0.93

 predators

0.92

 adverse

0.92

 erosion

0.92

 unwelcome

0.91

Activations Density 0.108%

terms related to protection or defense against various threats

phrases related to protection or safeguarding against various threats

No Comments

No Known Activations