INDEX

Explanations

phrases related to triggering events or actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "trigger" and its variations

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

apest

-0.84

ensable

-0.81

apolis

-0.73

esan

-0.70

egal

-0.70

cipled

-0.68

hemat

-0.68

 Cutler

-0.67

nian

-0.67

atable

-0.66

POSITIVE LOGITS

 triggering

1.01

 triggers

0.97

trigger

0.92

 warnings

0.88

 trigger

0.85

 triggered

0.81

 alarms

0.77

witz

0.76

prises

0.74

 cascade

0.74

Activations Density 0.078%

phrases related to triggering events or actions

occurrences of the word "trigger" and its variations

No Comments

No Known Activations