INDEX

Explanations

names of athletes and sports players, particularly focusing on their performance and career details

oai_token-act-pair · gpt-3.5-turbo

the verb "was"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

PsyNetMessage

-0.83

aceae

-0.81

ollah

-0.69

ographers

-0.67

encies

-0.67

ulence

-0.67

 spans

-0.66

artments

-0.66

zhen

-0.65

ologies

-0.65

POSITIVE LOGITS

 sidelined

1.22

 injured

1.21

 drafted

1.14

 ejected

1.13

 reunited

1.11

 traded

1.10

 sacked

1.09

 hampered

1.08

 inactive

1.07

 diagnosed

1.05

Activations Density 0.139%

names of athletes and sports players, particularly focusing on their performance and career details

the verb "was"

No Comments

No Known Activations