INDEX

Explanations

terms related to measuring instruments, particularly gauges

oai_token-act-pair · gpt-3.5-turbo

references to measurement or assessment tools, particularly those related to gauging quality or performance

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

urally

-0.85

urous

-0.82

rophic

-0.78

arily

-0.77

emort

-0.77

æĸ¹

-0.75

urrent

-0.74

ulent

-0.73

uring

-0.72

rophe

-0.72

POSITIVE LOGITS

 gauge

1.01

gau

0.93

 needle

0.84

 needles

0.77

 Pens

0.76

cised

0.72

 stations

0.72

 pens

0.71

 refill

0.70

 readings

0.70

Activations Density 0.073%

terms related to measuring instruments, particularly gauges

references to measurement or assessment tools, particularly those related to gauging quality or performance

No Comments

No Known Activations