INDEX

Explanations

terms related to military offensives and battles

oai_token-act-pair · gpt-3.5-turbo

references to military offensives and advances in conflict scenarios

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

 Lifetime

-1.02

 actresses

-0.77

 positives

-0.75

 Autism

-0.75

 Greenberg

-0.74

Grade

-0.73

 Substance

-0.69

 Parables

-0.68

 Emmy

-0.68

 actress

-0.67

POSITIVE LOGITS

 skirm

1.15

 besie

1.12

 patrols

1.03

 bombardment

1.02

 encamp

0.99

 bombard

0.98

 raiding

0.95

combat

0.94

alions

0.94

 artillery

0.93

Activations Density 0.283%

terms related to military offensives and battles

references to military offensives and advances in conflict scenarios

No Comments

No Known Activations