INDEX

Explanations

words 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

APTER

-0.75

spring

-0.75

 Alive

-0.73

 Traps

-0.72

flies

-0.71

 Frie

-0.69

pace

-0.68

 Occupations

-0.68

eon

-0.68

ymes

-0.67

POSITIVE LOGITS

 unilateral

1.05

 disarm

0.99

ilateral

0.99

ism

0.95

 unilaterally

0.85

 ceasefire

0.80

ilaterally

0.80

 coercive

0.80

ities

0.77

ized

0.75

Activations Density 0.012%

words related to unilateral actions or decisions

terms related to unilateral actions or decisions

No Comments

No Known Activations