INDEX

Explanations

phrases related to time frames or durations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating time-related expectations or delays

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

ENG

-0.85

VIDEO

-0.74

advertisement

-0.71

haw

-0.68

atic

-0.68

rather

-0.67

Lenin

-0.66

JV

-0.65

¤

-0.64

ãĤ´ãĥ³

-0.64

POSITIVE LOGITS

 returning

0.88

 anyone

0.87

 deciding

0.84

 resume

0.76

 settling

0.76

 anybody

0.76

 retiring

0.76

 encountering

0.72

 resumes

0.72

we

0.70

Activations Density 0.071%

phrases related to time frames or durations

phrases indicating time-related expectations or delays

No Comments

No Known Activations