INDEX

Explanations

instances where the word "count" is followed by a number

oai_token-act-pair · gpt-3.5-turbo

instances of counting or numerical references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\\\\\\\\

-0.77

Thumbnail

-0.72

nered

-0.69

avage

-0.69

forum

-0.67

ĨĴ

-0.65

Mars

-0.65

nery

-0.64

redo

-0.62

feel

-0.61

POSITIVE LOGITS

GGGG

0.66

 positives

0.65

 cere

0.65

Sequ

0.64

 elapsed

0.64

 Tens

0.63

 probabilities

0.63

Tac

0.62

 Trib

0.61

 milliseconds

0.61

Activations Density 0.089%

instances where the word "count" is followed by a number

instances of counting or numerical references

No Comments

No Known Activations