INDEX

Explanations

instances of the word "overly" with varying levels of intensity

oai_token-act-pair · gpt-3.5-turbo

instances of the word "overly" and related terms that indicate excessiveness

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

iens

-0.79

 Bullets

-0.77

igi

-0.73

 Tycoon

-0.72

itudinal

-0.70

ians

-0.70

raltar

-0.68

 Rite

-0.67

riots

-0.67

alion

-0.66

POSITIVE LOGITS

 burdens

0.84

 complicate

0.82

 optimistic

0.79

 simplistic

0.79

assi

0.77

 reliant

0.76

 intoxicated

0.75

 priced

0.75

lax

0.74

 sensitive

0.74

Activations Density 0.017%

instances of the word "overly" with varying levels of intensity

instances of the word "overly" and related terms that indicate excessiveness

No Comments

No Known Activations