INDEX

Explanations

mentions of political figures like Ted Cruz, Marco Rubio, and other politicians

oai_token-act-pair · gpt-3.5-turbo

names of political figures and candidates

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

ĸļ

-0.91

alam

-0.81

LTD

-0.76

pmwiki

-0.75

adobe

-0.75

ORPG

-0.75

hare

-0.74

ept

-0.74

uckland

-0.73

-0.70

POSITIVE LOGITS

 Clinton

1.05

 Rodham

0.94

 Clintons

0.93

 Sanders

0.93

 supporters

0.92

 Obama

0.91

Clinton

0.90

 Trump

0.89

 Biden

0.89

 TAMADRA

0.88

Activations Density 0.146%

mentions of political figures like Ted Cruz, Marco Rubio, and other politicians

names of political figures and candidates

No Comments

No Known Activations