INDEX

Explanations

references to legislative actions or regulations

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

Firstly

-1.20

 whilst

-1.15

 Whilst

-1.14

 util

-0.94

 recognise

-0.92

 analyse

-0.88

 Firstly

-0.88

 realise

-0.84

gement

-0.82

uminium

-0.81

POSITIVE LOGITS

 nonprofits

0.90

 sued

0.86

 Whitman

0.83

 congressional

0.82

 Grassley

0.82

 subpoen

0.82

 lawsuits

0.80

 POLITICO

0.79

 nonprofit

0.79

 Giuliani

0.79

Activations Density 0.838%

references to legislative actions or regulations

No Comments

No Known Activations