INDEX

Explanations

conditional statements indicating hypothetical scenarios

oai_token-act-pair · gpt-3.5-turbo

hypothetical scenarios or conditional statements involving actions and their consequences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

gae

-0.67

*/(

-0.66

DX

-0.62

inventoryQuantity

-0.61

iatus

-0.61

lies

-0.60

Latest

-0.57

ãĤ£

-0.56

Def

-0.55

ilial

-0.55

POSITIVE LOGITS

would

1.56

 would

1.45

 wouldn

1.42

 Would

1.35

 Wouldn

1.17

Would

1.10

'd

1.04

could

0.97

 could

0.85

might

0.82

Activations Density 0.948%

conditional statements indicating hypothetical scenarios

hypothetical scenarios or conditional statements involving actions and their consequences

No Comments

No Known Activations