INDEX

Explanations

phrases related to survey results and statistics

oai_token-act-pair · gpt-3.5-turbo

terms related to polling and survey results

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

ufact

-0.78

inventoryQuantity

-0.76

via

-0.74

 sidx

-0.71

brance

-0.71

xtap

-0.67

ascus

-0.67

ipal

-0.67

phe

-0.65

uli

-0.65

POSITIVE LOGITS

 widespread

0.71

 discrepancies

0.71

 that

0.66

 conclusive

0.66

 anomalies

0.65

 majorities

0.65

 trillions

0.64

 inconsistencies

0.64

 billions

0.64

 upwards

0.64

Activations Density 0.148%

phrases related to survey results and statistics

terms related to polling and survey results

No Comments

No Known Activations