INDEX

Explanations

keywords related to news reports or articles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "reports" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arden

-0.67

 Chamberlain

-0.65

antics

-0.65

awar

-0.63

 bonding

-0.63

inh

-0.63

 Nadu

-0.63

ojure

-0.63

ucky

-0.61

 manslaughter

-0.61

POSITIVE LOGITS

 quoting

0.79

etter

0.75

 reports

0.74

Rum

0.73

udo

0.73

 emanating

0.72

print

0.71

orial

0.70

 indicate

0.67

 citing

0.66

Activations Density 0.058%

keywords related to news reports or articles

occurrences of the word "reports" in various contexts

No Comments

No Known Activations