INDEX

Explanations

keywords related to news articles and political events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "PA" related to news agency references

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

lings

-0.89

tie

-0.85

naire

-0.75

worms

-0.72

worldly

-0.71

nets

-0.69

line

-0.68

icity

-0.68

 nets

-0.67

lers

-0.66

POSITIVE LOGITS

UL

1.06

WN

1.06

INT

0.98

BLE

0.94

GE

0.90

BILITY

0.89

IRED

0.88

ignt

0.84

veyard

0.82

UNCH

0.81

Activations Density 0.020%

keywords related to news articles and political events

occurrences of the abbreviation "PA" related to news agency references

No Comments

No Known Activations