INDEX

Explanations

mentions of locations or specific places

oai_token-act-pair · gpt-3.5-turbo

references to educational experiences and interactions with classmates

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

xit

-0.67

-0.61

 Hezbollah

-0.59

 deterrence

-0.59

anwhile

-0.58

 rivals

-0.57

worthiness

-0.55

 threatens

-0.53

POSITIVE LOGITS

 myself

1.03

my

0.91

 haha

0.81

:)

0.77

:-)

0.71

My

0.67

 blogging

0.66

my

0.66

nesday

0.66

 Soup

0.65

Activations Density 2.092%

mentions of locations or specific places

references to educational experiences and interactions with classmates

No Comments

No Known Activations