INDEX

Explanations

phrases that start with "we" or "I" followed by statements or actions

oai_token-act-pair · gpt-3.5-turbo

the first-person plural pronoun "we" 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 @ 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

netflix

-0.67

 Publication

-0.65

 totality

-0.61

nesota

-0.60

 citation

-0.60

INGTON

-0.60

cum

-0.58

REDACTED

-0.56

ions

-0.56

POSITIVE LOGITS

've

0.97

arily

0.97

're

0.94

'll

0.92

blogs

0.90

eding

0.90

ldon

0.90

asel

0.89

athered

0.88

ighed

0.87

Activations Density 0.238%

phrases that start with "we" or "I" followed by statements or actions

the first-person plural pronoun "we" in various contexts

No Comments

No Known Activations