INDEX

Explanations

terms related to a specific financial institution

oai_token-act-pair · gpt-3.5-turbo

references to the term "Commonwealth" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

gered

-0.98

paces

-0.93

geon

-0.90

gers

-0.87

steen

-0.84

upper

-0.83

ebus

-0.82

Tonight

-0.82

ema

-0.82

ear

-0.82

POSITIVE LOGITS

 Commonwealth

1.06

 Reserve

0.81

enary

0.79

sylvania

0.76

 Antarctic

0.75

 republic

0.74

 Scientific

0.74

ortium

0.74

wide

0.71

 capitals

0.69

Activations Density 0.016%

terms related to a specific financial institution

references to the term "Commonwealth" and related concepts

No Comments

No Known Activations