INDEX

Explanations

references to leadership positions, specifically the role of a chief in various contexts

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

phis

-0.85

nikov

-0.85

lishes

-0.83

lished

-0.80

ajor

-0.72

aughs

-0.70

ppo

-0.69

etimes

-0.69

lihood

-0.69

phia

-0.68

POSITIVE LOGITS

 executive

1.13

doms

0.94

 Executive

0.90

 executives

0.87

iary

0.85

 negotiator

0.80

 Operating

0.76

 administrative

0.76

 strategist

0.75

 planner

0.75

Activations Density 0.318%

references to leadership positions, specifically the role of a chief in various contexts

No Comments

No Known Activations