INDEX

Explanations

references to hotels

oai_token-act-pair · gpt-3.5-turbo

references to hotels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.76

 Anarchy

-0.76

nir

-0.73

İĭ

-0.72

 advers

-0.72

alys

-0.68

nan

-0.68

sha

-0.66

alogy

-0.66

 Izan

-0.64

POSITIVE LOGITS

 rooms

1.04

 accommodations

0.96

 Hotel

0.91

 hotel

0.90

 guests

0.89

 occupancy

0.88

 room

0.86

 hotels

0.85

 resorts

0.84

 lobb

0.81

Activations Density 0.032%

references to hotels

references to hotels

No Comments

No Known Activations