INDEX

Explanations

verbs related to rescue or emergency services

oai_token-act-pair · gpt-3.5-turbo

references to rescue operations and related terms

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

heid

-0.77

 Belt

-0.77

 Kane

-0.75

 Sheen

-0.72

 Tate

-0.71

 Celt

-0.70

PAX

-0.70

 Gates

-0.68

 Dish

-0.67

 Hutchinson

-0.66

POSITIVE LOGITS

uers

1.32

ategor

1.14

aled

1.13

ues

1.13

outed

1.13

ission

1.12

hett

1.10

abulary

1.09

aped

1.06

oded

1.05

Activations Density 0.017%

verbs related to rescue or emergency services

references to rescue operations and related terms

No Comments

No Known Activations