INDEX

Explanations

numerical references to future years, especially related to environmental targets or predictions

oai_token-act-pair · gpt-3.5-turbo

references to specific years, particularly 2030 and 2050

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

afort

-0.81

verbs

-0.73

abilia

-0.71

uid

-0.69

ando

-0.67

tub

-0.66

isy

-0.66

yl

-0.66

ql

-0.64

iqu

-0.64

POSITIVE LOGITS

1.00

0.93

ãĤ¼ãĤ¦ãĤ¹

0.92

 onwards

0.82

abad

0.82

 onward

0.81

0.76

 Ceres

0.74

Activations Density 0.015%

numerical references to future years, especially related to environmental targets or predictions

references to specific years, particularly 2030 and 2050

No Comments

No Known Activations