INDEX

Explanations

phrases related to potential or future actions and outcomes

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

 instantly

-0.71

pmwiki

-0.68

 sudden

-0.66

pecially

-0.61

 istg

-0.61

erity

-0.59

Wall

-0.59

Drug

-0.59

ulence

-0.58

 coincided

-0.58

POSITIVE LOGITS

 finalized

0.79

 refinement

0.77

 completion

0.75

pleted

0.73

 refining

0.73

 reconcil

0.73

pees

0.71

 figuring

0.70

TBD

0.69

PDATED

0.68

Activations Density 1.513%

phrases related to potential or future actions and outcomes

No Comments

No Known Activations