INDEX

Explanations

key concepts related to responsibility, policy, and measurable impacts in social contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

 Know

-0.60

selves

-0.59

iatus

-0.59

ECA

-0.59

zan

-0.57

+.

-0.55

ochet

-0.54

poon

-0.53

orea

-0.53

isse

-0.53

POSITIVE LOGITS

 becomes

0.87

 disappears

0.85

 varies

0.84

iest

0.79

 remains

0.78

 ceases

0.77

 goes

0.75

 consists

0.74

 arises

0.73

 evolves

0.73

Activations Density 0.295%

key concepts related to responsibility, policy, and measurable impacts in social contexts

No Comments

No Known Activations