INDEX

Explanations

phrases related to hitting or striking something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "hits" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

verning

-0.72

 consent

-0.71

ether

-0.66

 clothed

-0.65

 constituted

-0.65

AppData

-0.64

inus

-0.61

 concealed

-0.61

PT

-0.60

astern

-0.60

POSITIVE LOGITS

 hits

3.66

 Hits

2.71

hit

2.33

hit

1.74

 hitting

1.73

 slams

1.60

 strikes

1.60

Hit

1.57

 blows

1.53

 misses

1.53

Activations Density 0.009%

phrases related to hitting or striking something

occurrences of the word "hits" in various contexts

No Comments

No Known Activations