INDEX

Explanations

words related to precautionary measures or safety measures

oai_token-act-pair · gpt-3.5-turbo

terms related to safety measures and precautions

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

ettle

-0.81

zie

-0.77

KER

-0.70

peak

-0.66

spons

-0.65

 Kinn

-0.65

writ

-0.64

NetMessage

-0.63

lined

-0.61

partisan

-0.61

POSITIVE LOGITS

 precaution

1.23

autions

1.05

ary

1.04

 precautions

1.01

azard

0.90

ously

0.87

 safeguards

0.76

 measures

0.74

 safeguard

0.72

ariat

0.70

Activations Density 0.029%

words related to precautionary measures or safety measures

terms related to safety measures and precautions

No Comments

No Known Activations