INDEX

Explanations

words related to influence, both positive and negative

oai_token-act-pair · gpt-3.5-turbo

references to influence, particularly its significance and effects in various contexts

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

leigh

-0.74

eared

-0.74

ITIES

-0.73

Quotes

-0.72

asar

-0.72

DEF

-0.72

ft

-0.72

adapt

-0.72

heart

-0.71

TAG

-0.71

POSITIVE LOGITS

 pedd

1.32

 exerted

1.00

 influencing

0.94

 shaping

0.94

 cooker

0.87

 sway

0.87

 influence

0.86

 exercised

0.80

enza

0.74

orship

0.74

Activations Density 0.061%

words related to influence, both positive and negative

references to influence, particularly its significance and effects in various contexts

No Comments

No Known Activations