INDEX

Explanations

phrases related to global events, agreements, and political activities

oai_token-act-pair · gpt-3.5-turbo

terms related to significant global or political issues

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

itars

-0.83

lees

-0.82

hops

-0.81

 Bits

-0.80

nces

-0.80

urches

-0.79

 acron

-0.79

redients

-0.78

 Rooms

-0.76

aunts

-0.75

POSITIVE LOGITS

 foothold

1.01

 standpoint

0.96

 basis

0.93

 solution

0.89

 showdown

0.89

 agenda

0.88

 presidency

0.86

 caliphate

0.86

 perspective

0.86

 mindset

0.85

Activations Density 0.489%

phrases related to global events, agreements, and political activities

terms related to significant global or political issues

No Comments

No Known Activations