INDEX

Explanations

comparisons and evaluations in text

oai_token-act-pair · gpt-3.5-turbo

comparisons or contrasts between different subjects or ideas

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

interrupted

-0.71

Leod

-0.71

arten

-0.67

qui

-0.66

dimension

-0.66

iol

-0.65

panic

-0.63

hes

-0.60

arching

-0.57

letters

-0.57

POSITIVE LOGITS

 considering

0.86

Gaw

0.73

 honestly

0.73

}:

0.70

 Especially

0.70

especially

0.69

 imagine

0.67

 folks

0.66

WM

0.66

 compared

0.66

Activations Density 0.451%

comparisons and evaluations in text

comparisons or contrasts between different subjects or ideas

No Comments

No Known Activations