INDEX

Explanations

keywords related to news coverage

oai_token-act-pair · gpt-3.5-turbo

mentions of "coverage" in various contexts

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

rir

-0.72

 Sabha

-0.70

geries

-0.70

 slightest

-0.70

itialized

-0.67

entle

-0.67

 Tale

-0.67

gery

-0.64

batch

-0.62

Â¯Â¯

-0.62

POSITIVE LOGITS

 Coverage

1.02

 coverage

0.95

verage

0.84

krit

0.77

cov

0.77

 Everywhere

0.73

atcher

0.71

orship

0.70

 Journalists

0.69

irtual

0.69

Activations Density 0.028%

keywords related to news coverage

mentions of "coverage" in various contexts

No Comments

No Known Activations