INDEX

Explanations

mentions of family members or characters such as "Aunt" in the text

oai_token-act-pair · gpt-3.5-turbo

references to "Aunt" and associated familial themes

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

vous

-0.96

eled

-0.79

atile

-0.77

ingen

-0.76

untled

-0.73

ified

-0.72

dfx

-0.72

ipping

-0.72

oting

-0.71

ipped

-0.71

POSITIVE LOGITS

Reviewer

1.03

 Difficulty

0.82

 Controller

0.81

Plug

0.81

Solution

0.81

ifacts

0.81

 Rend

0.79

 Defin

0.79

 Decay

0.79

 Annotations

0.78

Activations Density 0.144%

mentions of family members or characters such as "Aunt" in the text

references to "Aunt" and associated familial themes

No Comments

No Known Activations