INDEX

Explanations

references to the name "Ge" with different variations in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the abbreviation "Ge" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Interstitial

-1.07

ioned

-0.85

sburgh

-0.83

Topic

-0.76

kefeller

-0.75

æł

-0.72

INGTON

-0.70

igham

-0.70

âĶĢâĶĢ

-0.69

aneous

-0.69

POSITIVE LOGITS

cko

1.02

hog

0.96

gebra

0.94

elong

0.91

orget

0.91

og

0.91

ffen

0.90

Ge

0.89

ographical

0.87

ogly

0.86

Activations Density 0.012%

references to the name "Ge" with different variations in the text

mentions of the abbreviation "Ge" in various contexts

No Comments

No Known Activations