INDEX

Explanations

locations mentioned in close proximity to an event or object

oai_token-act-pair · gpt-3.5-turbo

instances of the word "near" indicating proximity to locations or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

BILL

-0.75

etti

-0.74

Wire

-0.71

alian

-0.70

Percent

-0.69

ilus

-0.69

 arrang

-0.68

UX

-0.67

NT

-0.66

azeera

-0.66

POSITIVE LOGITS

shore

1.02

sighted

0.92

 misses

0.86

 Bethlehem

0.82

 midnight

0.78

 Coff

0.76

 Naples

0.75

ctic

0.75

 campus

0.75

roads

0.72

Activations Density 0.030%

locations mentioned in close proximity to an event or object

instances of the word "near" indicating proximity to locations or events

No Comments

No Known Activations