INDEX

Explanations

terms related to unilateral actions or decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to unilateral actions or decisions

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

 Traps

-0.73

ĺħ

-0.71

APTER

-0.71

wives

-0.68

nets

-0.67

 Tycoon

-0.67

 Eggs

-0.67

Life

-0.66

 Occupations

-0.66

 Cooking

-0.66

POSITIVE LOGITS

 disarm

0.92

 unilateral

0.92

ism

0.85

 unilaterally

0.85

 ceasefire

0.75

 guiActiveUn

0.74

ilaterally

0.73

ilateral

0.71

 declaration

0.70

 coercive

0.68

Activations Density 0.013%

terms related to unilateral actions or decisions

terms related to unilateral actions or decisions

No Comments

No Known Activations